The agent-listing scanner (AGT) emits an always-loaded per-turn token cost
("Agent description is long, re-sent every turn in the always-loaded listing";
scanner category 'token-efficiency', "the dominant single always-loaded
source"). But SCANNER_TO_CATEGORY in humanizer.mjs had no AGT entry, so its
findings fell through to the 'Other' fallback (humanizer.mjs:140) — a bucket
that isn't even in the analyzer-agent's category list. Neither the scanner
prefix nor the per-finding category ('token-efficiency' is not in
CATEGORY_TO_IMPACT) resolved AGT to its true impact.
Same class as M-BUG-16/15: a finding type without its matching humanizer
mapping landing on a default that mismatches its own evidence. The analogous
SKL body finding correctly buckets "Wasted tokens"; AGT (the same always-loaded
token-waste mechanism) silently landed under the meaningless "Other".
Found during analyze-prep premise-verification of the linkedin-posts scan: the
3 AGT findings bucketed "Other" while the analogous SKL findings bucketed
"Wasted tokens".
Fix: add AGT: 'Wasted tokens' to SCANNER_TO_CATEGORY, alongside TOK/CPS/SKL.
RED-first (extended the Wasted-tokens category test to include AGT; the 'Other'
fallback test still uses a synthetic 'XXX' scanner, unaffected). Frozen v5.0.0
untouched (AGT post-dates it; humanizer bypassed for --raw/--json); no
default-output snapshot contains AGT -> 0 regen. Suite 1359/0.
Verified end-to-end on linkedin-posts: 3 AGT findings now "Wasted tokens", 0
"Other" remaining, 28 findings unchanged (category-only). All 16 orchestrator
scanner prefixes now covered by the category map (class closed).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01683eAqVecv9VZfQzL8CQ9h
The skill-listing check emits a third finding for an oversized skill BODY
(v5.11 B7, RAW title "Skill body is large (loads on demand when the skill
runs)"). The body is an ON-DEMAND cost — it loads only when the skill is
invoked, not the always-loaded listing Claude reads every turn. The scanner is
careful to distinguish the two (RAW title + comment + evidence note).
But the humanizer-data SKL.static map had no entry for this title, so it fell
through to SKL._default ("A skill is using more of the listing budget than it
should"). The humanized title therefore claimed a listing-budget cost and
directly contradicted the finding's own humanized evidence ("loads ON DEMAND
only ... NOT every turn like the always-loaded listing") — the same internal
contradiction class as M-BUG-15/M-BUG-14, and the same "new finding type added
without a matching humanizer entry" gap the scanner checklist warns about.
Found by finding-granularity premise-verification of the linkedin-posts scan
before feeding it to the analyze pipeline (the prior session's pass focused on
the GAP findings and did not catch the SKL fall-through).
- humanizer-data.mjs: add SKL.static entry for "Skill body is large (loads on
demand when the skill runs)" with on-demand-correct title ("A skill's body is
large (it loads only when that skill runs)"), description, and recommendation.
No listing-budget language; tier1/tier3 forbidden-word checks pass.
- RED-first tests at both layers: humanizer.test.mjs (humanizeFinding path:
title is not the listing-budget _default, conveys on-demand body) and
humanizer-data.test.mjs (static entry exists, on-demand-correct).
RAW envelope unaffected (humanizer bypassed for --raw/--json), frozen v5.0.0
snapshots untouched, default-output fixtures contain no oversized-body skill so
no snapshot regen. Suite 1357->1359/0 (+2).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01683eAqVecv9VZfQzL8CQ9h
The t2_3 ("No path-scoped rules") and t3_6 ("No subagent isolation")
feature-gap checks iterate a collection (rule files / agent files) and return
false for an EMPTY one — so they fire even when the user has zero rules / zero
subagents, the same state their presence-gap siblings flag. But the humanized
titles presupposed the feature already exists:
- "Your rules all load on every conversation" (with zero rules)
- "Your subagents share Claude's main work folder" (with zero subagents)
The second directly contradicts GAP-005 "You haven't set up any specialized
helper agents yet" in the same report — a user cannot simultaneously have no
subagents and have subagents that lack isolation. Found by dogfooding the
analyze pipeline against linkedin-posts (premise-verifying each finding before
trusting the analyzer-agent's report).
Decided fix = align the two titles with the house "You haven't set up X yet"
absence framing (state-neutral: honest for both the zero-state and the
has-but-unconfigured state), NOT a base-feature presence gate in the scanner —
that would change the frozen v5.0.0 marketplace-medium baseline (zero
rules/agents, freezes these gaps firing) and break the RAW byte contract.
Mirrors M-BUG-14's humanizer-layer, copy-only approach.
- humanizer-data.mjs: title "Your rules all load on every conversation" ->
"You haven't set up path-scoped rules yet"; title "Your subagents share
Claude's main work folder" -> "You haven't set up subagent isolation yet".
description + recommendation unchanged. t3_5/t3_7 ("Your skills don't ...")
left as-is: their possessive is correct in the common case where skills
exist; the zero-skills edge is latent, not manifest here.
- RED-first unit test pins both titles existence-neutral (forbids "your rules
all load" / "your subagents"; feature still named).
Frozen v5.0.0 snapshots untouched (RAW bypasses humanizer); default-output
snapshot regenerated (2 titles only, no collateral). Verified on linkedin-posts:
GAP-004/005/011 now all consistently absence-framed. Suite 1356->1357/0.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01683eAqVecv9VZfQzL8CQ9h
The t2_2 feature-gap check is a pure presence check (rules file OR @import
present) with no length gate, consistent with its t2_3/t2_4/t2_5 siblings.
But the humanized copy claimed the file is "one big block" and that splitting
makes it "easier on the loading time" — an unconditional size/load-cost
overclaim. For a ~625-token non-modular CLAUDE.md the load saving is trivial,
so the description lied. Found by dogfooding feature-gap against linkedin-posts.
Decided fix = copy-softening, NOT a length gate in t2_2 (that would make it the
only size-gated check among the presence-check siblings + risks byte-stability
if a short non-modular CLAUDE.md fixture exists in snapshots).
- humanizer-data.mjs: title "one big block" -> "all live in one file";
description drops "long"/"loading time", keeps the honest structural
"split into linked files with @import or .claude/rules/" framing.
recommendation unchanged.
- RED-first unit test pins the size-neutral copy (no "big"/"long"/"loading
time" in title/desc, structural split framing kept).
Frozen v5.0.0 snapshots untouched (RAW envelope bypasses humanizer); SC-5
default-output byte-stable (no non-modular GAP finding in those fixtures).
Suite 1355->1356/0.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01683eAqVecv9VZfQzL8CQ9h
The CC settings schema is passthrough (verified against the 2.1.193 binary): it
forwards unrecognized keys unchanged rather than rejecting them, so an arbitrary
unknown key is valid/forward-compatible, not an error — the finding's "silently
ignored" claim was factually wrong. The only real risk is a TYPO of a real key
(the intended setting then silently has no effect). Fix: flag an unknown key only
when it closely matches a known key (new levenshtein helper; edit distance <= 2,
both keys >= 4 chars); severity medium -> low; honest passthrough framing in the
scanner + humanizer. Also refreshed KNOWN_KEYS with 6 binary-verified keys
(agentPushNotifEnabled, remoteControlAtStartup, skipAutoPermissionPrompt,
skipDangerousModePermissionPrompt, skipWorkflowUsageWarning, tui). Suite 1341/0
(+12). Frozen v5.0.0 snapshots untouched (0 CA-SET findings there), no re-seed.
Dogfood ~/.claude/settings.json 6->0 (all 6 keys above were false unknown-key
findings; 0 typo flags introduced across 167 walked files).
CLAUDE.md token estimates counted block-level <!-- --> HTML comments toward
always-loaded tokens, but CC strips them before injection (preserved only inside
code fences, per code.claude.com/docs/en/memory). Fix: new stripInjectedHtmlComments
+ effectiveMemoryBytes in active-config-reader; the CML cascade (walkClaudeMdCascade)
and token-hotspots now size CLAUDE.md from effective (stripped) bytes, while raw byte
figures stay honest. Block-level only — inline comments retained (conservative,
verified scope). Suite 1329/0 (+13). Frozen v5.0.0 snapshots untouched (no fixture
has <!--), no re-seed. Dogfood ~/.claude CLAUDE.md ~3386->3301 tok (~85 tok discount,
matches worklist prediction).
A directory named `backups` holds backup COPIES, not live config, so walking
it during a config audit produces stale findings. config-audit's own session
backups (~/.claude/config-audit/backups/<ts>/files/.../CLAUDE.md) were the
canonical case: a ~/.claude-scope audit walked 36 frozen config copies as if
live, polluting CPS (C3) and HKV/RUL (C6) results. Same non-live-noise family
as M-BUG-2.
- Add `backups` to SKIP_DIRS (broad, name-based — consistent with vendor/dist/
.cache): the rule is general, a backups/ dir is never live config.
TDD: 2 failing tests (no config under backups/ discovered + backups/ counted
as skipped) -> green; a third asserts live config beside the backups tree is
still discovered. Full suite 1310/0 (+3). Byte-stable: no fixture is named
`backups` and `backups` appears in zero frozen snapshots, so v5.0.0 + SC-5 +
default-output outputs are unchanged. Dogfooding ~/.claude: files under
/backups/ drop from 36 -> 0; 717 live config files retained.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EnUvKEqyEa1m9gy6Aqhdqq
enumerateAgents previously counted every .md in an agents dir as an
always-loaded agent. Per the official CC subagents docs, CC registers a
subagent only when its frontmatter declares both name and description, scans
agents dirs recursively, and (at a HOME self-scan) must not count
~/.claude/agents twice.
- M-BUG-5: require valid name+description frontmatter; frontmatter-less files
are registration no-ops costing 0 always-loaded tokens. Fixes the user-agent
over-count (this machine: 13 -> 0).
- M-BUG-3: listMarkdownFiles gains opt-in recursion; enumerateAgents recurses
so agents in subfolders (agents/review/x.md) are counted, matching CC.
- M-BUG-4: configDirs dedupes project==user paths, so a `manifest --global`
self-scan (repoPath===$HOME) counts ~/.claude once (user scope), killing the
spurious "project 13" double-count. Benefits rules/agents/output-styles.
TDD: 4 failing tests -> green. Full suite 1305/0; --json/--raw byte-stable,
frozen v5.0.0 + SC-5 + default-output snapshots untouched (no snapshot records
agent enumeration rows).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EnUvKEqyEa1m9gy6Aqhdqq
active-config-reader walked ~/.claude/plugins/marketplaces and ignored both the
enabledPlugins toggle and the polyrepo cache layout. On a polyrepo machine it
counted disabled/uninstalled marketplaces plugins as "active" while MISSING the
actually-enabled plugins installed under plugins/cache. This corrupted the agent
listing and every pluginList consumer (manifest, AGT, whats-active, hooks, rules).
Now: when installed_plugins.json is present, inject only plugins that are in the
manifest AND enabledPlugins[key]===true, each resolved to its active installPath
(incl. cache/). When the manifest is absent (fixtures/pre-v2 installs), fall back
to the historic marketplaces walk rather than silently dropping config — mirrors
file-discovery.mjs's "trust installed_plugins.json" contract.
Verified on real machine: agent listing 114->104, ghost plugins (newsletter,
content-machine, harness, kiur, ...) gone, voyage/linkedin/ms-ai/okr now correctly
counted. Full suite 1301/0; byte-stable snapshots untouched (hermetic empty HOME).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CrTb8ktf1XZWEVwgz5MTTo
Completes the deferred B8 half. `--context-window auto` now probes the
configured model and calibrates SKL/CML budgets to its real window instead
of always falling back to the conservative advisory anchor.
- lib/context-window.mjs: pure modelToContextWindow() maps known 1M-tier
model IDs (Fable 5, Opus 4.8/4.7/4.6, Sonnet 4.6 — verified June 2026 —
plus the explicit [1m] tier tag, dated/provider-prefixed IDs, and the
opus/sonnet/fable aliases) to the 1M window; unknown/unconfirmed -> null
(caller keeps the conservative anchor). resolveContextWindow() auto branch
now probes opts.model: recognized -> auto-probed (not advisory); unknown
or unpinned -> auto-unresolved (advisory, pre-B8b behavior).
- lib/active-model.mjs (new): resolveActiveModel() reads the model the way
Claude Code resolves it — shell ANTHROPIC_MODEL override, then settings
cascade local > project > user. Injectable env, hermetic under test HOME.
- scan-orchestrator: resolves the active model only when the flag is `auto`
and threads it into resolveContextWindow; posture inherits via runAllScanners.
Default (no flag) and explicit --context-window <n> paths ignore the model
and stay byte-stable; frozen v5.0.0 + SC-5 snapshots untouched. TDD: 17 new
tests (context-window mapping/probe + active-model cascade). Suite 1296 green.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
SKL-002 (skill-listing budget) and CML char-budget now calibrate to a
resolved context window instead of always anchoring at 200k:
- resolveContextWindow(): --context-window <n> calibrates; 'auto' keeps the
conservative 200k anchor but marks advisory (model→window probing deferred
to B8b); no flag → 200k anchor, byte-identical to pre-B8 default.
- scaleForWindow(): linear off the 200k anchor (identity at the anchor).
- SKL + CML each keep an untouched default branch (window===200k && !advisory)
for byte-stability and a calibrated branch; advisory downgrades the budget
finding from a breach (low/medium) to info.
- Flag wired through scan-orchestrator + posture; runAllScanners resolves once
and threads { contextWindow } to scanners (others ignore the 3rd arg).
- CPS intentionally excluded: it has no window-anchored budget (fixed
150-line volatility heuristic), so there is nothing to calibrate.
15 new tests; e2e CLI verified (1M suppresses SKL-002, auto → info, default
unchanged); full suite 1279 green; snapshots byte-stable.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The B3a cache filter already exposes discovery.staleCacheVersions; surface them
as a finding so the user knows the superseded plugin versions are safe to delete.
Honesty (Verifiseringsplikt): the finding loads on ZERO turns, so it must NOT
read as a per-turn token cost. TOK normally humanizes to "Wasted tokens"; a new
per-finding category override ('plugin-cache-hygiene' -> "Dead config") plus a
dedicated humanizer translation ("Old plugin versions are sitting on disk (safe
to delete) ... cost zero tokens per turn ... housekeeping, not a performance
problem") keep the prose accurate instead of the generic "using more space"
default. evidence carries the explicit "zero live-context impact" note.
- token-hotspots: Pattern H emits CA-TOK (low) from discovery.staleCacheVersions
when stale versions exist (`--global`); silent otherwise.
- humanizer: CATEGORY_TO_IMPACT lets a finding's category override the
scanner-default impact label (raw `category` field unchanged -> --json/--raw
byte-stable). humanizer-data: honest static translation for the finding.
- Tests: finding fires/severity/category, lists stale keys + zero-impact note,
silent when none; humanizer override -> Dead config; honest translation locked.
- Docs: tokens command render note (disk-cleanup, not a token problem) +
--no-exclude-cache flag; README + CLAUDE.md rows (7 patterns, cache-aware).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Stale ~/.claude/plugins/cache versions polluted token-hotspots ranking and
inflated CNF duplicate-hook findings with config that loads on zero turns.
installPaths point INTO the cache, so a blunt "skip all of plugins/cache"
would drop ACTIVE plugins — the filter is therefore version-aware: it reads
the adjacent installed_plugins.json, keeps active version dirs, drops only
stale ones (and exposes them via discovery.staleCacheVersions for B3b).
- file-discovery: cacheVersionKey() + applyCacheFilter() (active vs stale via
installed_plugins.json; HOME-independent, derives the manifest from the cache
path); discoverConfigFiles/Multi gain { excludeCache } + staleCacheVersions.
Absent/unparseable manifest -> no filtering (never silently drop live config).
- token-hotspots-cli + scan-orchestrator: --exclude-cache (default ON for these
live-cost scans) / --no-exclude-cache restores the full walk.
- Tests: cacheVersionKey unit cases; stale-dropped/active-kept/no-manifest
discovery cases; CNF-drop proof (soft-spot verified, not assumed:
include=1 -> exclude=0 duplicate-hook findings).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Extend the campaign ledger with a machine-wide always-loaded token bill, the
pure data-model + aggregation half of B2. Deliberately does NOT do live I/O:
the cross-repo readActiveConfig sweep that populates real numbers is B2b.
Design — shared layer counted ONCE, structurally:
- Ledger root gets an optional `sharedGlobal` summary (the always-loaded layer
paid in every repo: global CLAUDE.md + agent listing + global MCP + unscoped
global rules + active plugins' always components), stored ONCE via the new
setSharedGlobal().
- Each repo entry gets an optional `tokens` summary (its PER-REPO delta only),
set via the new setRepoTokens(); addRepo now seeds `tokens: null` (mirrors
findingsBySeverity).
- rollUp() stays PURE and gains a `tokens` aggregate: machineWide = sharedGlobal
+ Σ(per-repo deltas), so the shared layer is counted exactly once by
construction — the structural guard against the historic double-count bug.
Plus a `byRepo` table ranked DESC by always-loaded cost ("most expensive
repos") with a deterministic name tie-break.
Summary shape mirrors manifest's summarizeByLoadPattern exactly
({always|onDemand|external|unknown: {tokens,count}}) so B2b wires in trivially.
Keeps rollUp pure (no filesystem I/O) → byte-stable, respects the THIN campaign
motor invariant. Chosen over the plan's literal "run readActiveConfig inside
rollUp" which would break both (operator-approved deviation).
- 8 new ledger tests incl. the counted-once regression guard + byRepo ranking.
- Updated addRepo shape test (+tokens:null) and campaign-cli EMPTY_ROLLUP.
- No frozen snapshot affected (campaign is v5.7, absent from v5.0.0 baselines).
Suite green: 1189 tests.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Completes Block 4 (4b backlog + 4c export/execution). Asymmetric: plan
export is new testable code; execution is pure reuse of the existing
per-repo implement/rollback (no new execution machinery), per the plan's
"reuse existing backup/rollback".
Plan export ("planer følger arbeidsstedet"):
- scanners/lib/campaign-export.mjs (pure, now injected, 8 tests):
planExportPath(repo,sessionId) -> <repo>/docs/config-audit-plan-<sessionId>.md
(sessionId-keyed so same-day re-audits never collide);
buildPlanExportDocument({...,now}) -> provenance header + verbatim plan.
- scanners/campaign-export-cli.mjs (-cli, read-only by default, 10 tests):
--repo resolves the repo's linked session, reads its action-plan.md,
assembles the doc, emits {exportable,problems,targetPath,document}. Two
gates -> exit 1 advisory: no-session-linked / no-action-plan. Writes the
file ONLY under opt-in --write (byte-faithful copy; the LLM never re-types
a 200-line plan). --sessions-dir override for hermetic tests; exit 0/1/3.
Command: commands/campaign.md gains an `export <path>` mode (Step 6:
preview -> approve -> --write), then routes the user to the existing
/config-audit implement (backup + verify) + rollback + set-status
implemented. Nothing auto-written (Verifiseringsplikt).
Byte-stable: lib + -cli + command-doc only -> scanner count stays 15,
agents 7, commands 21 (export is a mode, not a new command), SC-5 +
backcompat suite untouched. suite 1150->1168. Block 4a (migrateLedger)
still deferred to the first breaking schema change.
Docs: CLAUDE.md section + badge 1150->1168/65->67 files; README badge +
campaign row + Testing prose (fixed stale 1055/59 -> true 1168/67).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add the durable ledger that sits ABOVE individual config-audit sessions for a
machine-wide audit campaign: repo list + per-repo lifecycle (pending → audited →
planned → implemented) + a machine-wide roll-up by status and severity.
scanners/lib/campaign-ledger.mjs — same hybrid split as knowledge-refresh:
- PURE transforms (createLedger / addRepo / setRepoStatus / rollUp) with `now`
injected (YYYY-MM-DD, never the clock) → deterministic + unit-testable.
- soft validateLedger (returns {valid,errors}, never throws) for loaded data;
transforms throw on programmer error (invalid status, unknown path).
- thin IO shell (defaultLedgerPath / loadLedger→null-on-ENOENT / saveLedger).
- persists to ~/.claude/config-audit/campaign-ledger.json — OUTSIDE the plugin
dir (next to sessions/) so it survives uninstall/reinstall/upgrade.
- schemaVersion stamped from the start → cheap Block 4 migration.
THIN scope (Block 3a, operator-approved): ledger + roll-up + persistence only —
no CLI/command/execution (Blocks 3b/3c/4). Internal plumbing, byte-stable until
consumed: no `export async function scan` + lives in lib/ → scanner count stays
15, no orchestrator wiring, SC-5 unchanged.
tests/lib/campaign-ledger.test.mjs — 28 tests (TDD, red→green). Full hermetic
suite 1091→1119 green.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The 'living' half of the v5.7 living knowledge base. Same hybrid split as the
optimization lens (Chunk 2b): a deterministic, byte-stable, unit-tested core +
a web/judgment command shell.
- scanners/lib/knowledge-refresh.mjs: pure assessFreshness(register,
{referenceDate, staleAfterDays=90}) — age-based fresh/stale classification of
source.verified; referenceDate injected (never reads the clock) → fully
deterministic. 15 tests.
- scanners/knowledge-refresh-cli.mjs: -cli (NOT an orchestrated scanner →
scanner count stays 15, suite byte-stable). Read-only — never writes the
register, never hits the network. --reference-date/--stale-after/--dry-run,
exit 0/1/3. 8 tests.
- commands/knowledge-refresh.md (opus): CLI stale-report → re-verify each stale
entry by re-reading its source.url → poll CC changelog + Anthropic blog →
apply ONLY human-approved writes, then re-validate the register. No unverified
claim is ever auto-written (Verifiseringsplikt). Web-driven → not byte-stable.
No new agent, no new orchestrated scanner. Docs/badges: commands 19→20,
tests 1068→1091 (20 lib + 32 scanner test files). self-audit A/A, readmeCheck passed.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The recall+precision halves of the CA-OPT hybrid motor for the three
mechanism-fit cases the deterministic OPT scanner (2a) deliberately skips:
lifecycle→hook (BP-MECH-001), unscoped path-specific→rule (BP-MECH-002),
absolute "never"→permission (BP-MECH-004).
New:
- scanners/lib/lens-prefilter.mjs — cheap, recall-oriented line scan of the
CLAUDE.md body; detector names mirror the register lensCheck fields; skips
fenced code, gates the path class on an instruction verb. Pure + 13 tests.
- scanners/optimize-lens-cli.mjs — discovery + OPT scanner + pre-filter; attaches
only the CONFIRMED register entry to each candidate (unverifiable → dropped,
Verifiseringsplikt); emits {deterministic, candidates, register, counts}.
- agents/optimization-lens-agent.md — opus precision gate (7th agent, orange):
reads the real CLAUDE.md, drops low-confidence candidates, keeps only genuine
opportunities, cites register id + source.
- commands/optimize.md — /config-audit optimize orchestrates pre-filter→agent→report.
Agent-driven → deliberately NOT byte-stable (own command, outside the snapshot
suite). No new orchestrated scanner → scanner count stays 15. Counts: agents
6→7, commands 18→19, suite 1055→1068. Self-audit A/A unchanged, readmeCheck
passed (clean HOME). Plan: docs/v5.7-optimization-lens-plan.md.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add knowledge/best-practices.json: a machine-readable, provenance-stamped, schema-validated best-practices register — the source of truth for the upcoming v5.7 optimization lens (CA-OPT). 13 seed entries migrated from the v5.5 V-rows (loading-model + compaction facts) and the Anthropic 'Steering Claude Code' blog (mechanism-fit rules); each entry carries source.url + verified date + confidence. Only confirmed claims are user-facing (Verifiseringsplikt).
scanners/lib/best-practices-register.mjs: zero-dependency loader + validator (loadRegister/validateRegister/getEntry, native JSON.parse — not YAML, since the repo is zero-dep and yaml-parser.mjs can't parse arrays-of-objects). tests/lib/best-practices-register.test.mjs: 22 tests (schema, provenance integrity, negative cases, lookup).
Byte-stable: no scanner consumes the register yet (Chunk 2), so all scanner output is unchanged. Suite 1023->1045, self-audit A/A, readmeCheck passed. Full design: docs/v5.7-optimization-lens-plan.md.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
New orchestrated scanner output-style-scanner.mjs — first new family since
SKL. Three findings, each pinned to a CONFIRMED V-row of the steering-model
plan + re-verified against code.claude.com/docs/en/output-styles:
- CA-OST-001 (medium, V10): user/project custom style missing
keep-coding-instructions:true (default false) → silently strips built-in
software-engineering instructions when active. Scoped to user/project.
- CA-OST-002 (low, V11): plugin style with force-for-plugin:true overrides the
user's selected outputStyle. Verifiseringsplikt correction — the plan bullet
said "project/user style," but force-for-plugin is plugin-styles-only per the
docs, so the check keys on source==='plugin'.
- CA-OST-003 (medium): settings outputStyle matching no built-in
(Default/Explanatory/Learning/Proactive, case-insensitive) nor discovered
custom style → dead config.
Byte-stability — a scanner addition, not a field addition. Growing the
scanners array + scanners_ok cannot be hidden by a field strip, but re-seeding
frozen v5.0.0 (the SKL precedent) would now bake in B2's hotspot triple +
claudeMd drift. So, per the B2 lesson, frozen v5.0.0 snapshots are PRESERVED
and the OST entry is stripped at compare time via new
tests/helpers/strip-added-scanner.mjs (wired into json/raw-backcompat + the
Step 5/6 humanizer tests); only SC-5 default-output is regenerated (additive
OST entry, diff reviewed). OST is fixture-gated (no output styles on
marketplace-medium / hermetic HOME → silent).
Wiring: orchestrator; humanizer (OST→Configuration mistake) + humanizer-data
OST family (title-coupled); scoring (OST→Settings, keeps 10 areas). Suite
1012→1023 (+11). Badges: scanners 14, tests 1023, TRANSLATIONS families 15.
Lore swept: README, CLAUDE.md, scanner-internals, humanizer.md. self-audit A/A.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Annotate every ranked TOK hotspot with the load-pattern triple
(loadPattern/survivesCompaction/derivationConfidence):
- hotspotLoadPattern() maps each discovery `type` → a deriveLoadPattern kind.
Rules reuse activeConfig.rules for precise `scoped` handling; claude-md maps
by scope. Two new deriveLoadPattern kinds back the rest: `command`
(on-demand — body loads on /invoke) and `harness-config` (external —
settings/keybindings/.mcp.json/hooks.json/plugin.json configure the CLI, not
the model context, so they cost no per-turn context tokens). Honest split:
the .mcp.json FILE is external; the MCP server's tool schemas are a separate
`always` hotspot.
Byte-stability — the opposite of B1's manifest. token-hotspots IS a byte-equal
SC-6/SC-7 CLI, and its hotspots ride inside scan-orchestrator + posture, so the
change touched SIX frozen-v5.0.0 comparisons across five test files. Resolved by
preserving the frozen baselines: a shared tests/helpers/strip-hotspot-load-pattern.mjs
strips the additive triple before each byte-equal compare (proves the original
schema is byte-identical). SC-5 default-output snapshots (scan-orchestrator +
token-hotspots) regenerated — diff reviewed as additive-only.
Tests 1008→1012. Self-audit A/A, scanner count unchanged at 13 (C bumps to 14).
Completes v5.6 B (B1 manifest + B2 token-hotspots).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Foundation chunk of v5.6 "steering-model II" (internal plumbing for B/C;
no command-output change, so --json/--raw/SC-5/6/7 stay byte-stable, count
stays 13).
active-config-reader.mjs:
- deriveLoadPattern(kind,{scoped}) — pure helper mapping each source kind to
loadPattern {always,on-demand,external} + survivesCompaction {yes,no,n/a}
+ derivationConfidence {confirmed,inferred}, traced to the published
loading model (V-rows in docs/v5.5-steering-model-plan.md).
- enumerateRules / enumerateAgents / enumerateOutputStyles — the three
source kinds previously unenumerated (mirror enumerateSkills). Output-style
discovery is direct (not a new file-discovery type) to keep the discovery
surface stable.
- readActiveConfig now exposes rules/agents/outputStyles arrays + totals
counts/subtotals (folded into grandTotal).
yaml-parser.mjs:
- parseSimpleYaml now reads YAML block sequences (paths:\n - a), not just
inline paths:. An empty-valued key with no `- ` items stays null
(backcompat). Resolves a pre-existing RUL false-positive (a block-seq-scoped
rule was misread as unscoped) — fix flows through unchanged RUL code.
Tests +35 (961 -> 996): block-seq parser cases, RUL block-seq regression
(no-misflag + durability-fires), deriveLoadPattern table, three enumerators
(positive+negative). Amended two existing ACR asserts (top-level key shape +
grandTotal sum). self-audit A/A, readmeCheck passed, mismatches []. tests
badge 961+->996+; README testing prose de-staled (635/36 -> 996/56);
CLAUDE.md Foundation note.
B (manifest/tokens render + snapshot regen) and C (CA-OST, count->14)
deferred to their own sessions/GO.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
Extends the DIS scanner and its shared permission-rules lib with a third
documented Claude Code permission footgun. Verified verbatim against
code.claude.com/docs/en/permissions (fetched 2026-06-19).
CC's Tool(param:value) matching (2.1.178) is off-limits for a tool's own
canonicalizing field — CC ignores such a rule and emits a startup warning,
because e.g. Bash(command:rm *) is bypassable by a compound command. The
forbidden fields: command (Bash/PowerShell), file_path (Read/Edit/Write),
path (Grep/Glob), notebook_path (NotebookEdit), url (WebFetch).
- lib/permission-rules.mjs: new forbiddenParamRule(entry) returning
{ tool, key, hint } or null. Only the param:value form (colon present)
whose key equals the tool's forbidden field is flagged; Bash(npm:*),
WebFetch(domain:host), Agent(model:opus), and Bash(command) (no colon)
are left valid. FORBIDDEN_PARAMS map is the single source of truth.
- DIS: scans allow + deny + ask and splits severity by intent — deny/ask
hits are false security (medium: the block never applies), allow hits are
dead config (low: param:value matching is deny/ask-only). Two findings,
permissions-hygiene, CA-DIS-NNN.
- 11 new tests (7 lib, 4 DIS) + 1 fixture forbidden-param-permissions
(force-added past .gitignore .claude/). Suite 918 -> 929. Snapshot
unchanged (SC-5 byte-equal), contamination grep clean, gitleaks clean.
README/CLAUDE document the broadened DIS mandate; test badge synced.
self-audit: PASS, configGrade A 97, pluginGrade A 100, scanners 13.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
Extends the DIS scanner and its shared permission-rules lib with two
documented Claude Code permission footguns. Verified verbatim against
code.claude.com/docs/en/permissions (fetched 2026-06-19).
- lib/permission-rules.mjs: new isIneffectiveAllowGlob(entry) — unanchored
tool-name globs in permissions.allow (`*`, `B*`, `mcp__*`) that CC silently
skips ("does not auto-approve anything"); valid only as a glob-free
`mcp__<server>__*`. Shared with CNF.
- lib/permission-rules.mjs: dominates() now treats the `Tool(*)` deny-all glob
as equivalent to a bare deny (covers a bare allow) — CC: "Bash(*) is
equivalent to Bash ... both forms remove the tool from Claude's context".
- DIS: new finding "Ineffective allow wildcard — Claude Code ignores this rule"
(low, permissions-hygiene, CA-DIS-NNN); the existing dead-allow finding now
also catches a bare allow killed by a Tool(*) deny.
- 9 new tests (5 lib, 4 DIS) + 2 fixtures (force-added past .gitignore .claude/).
Suite 903 -> 912. Snapshot unchanged, contamination grep clean. README/CLAUDE/
scanner-internals document the broadened DIS mandate; test badge synced.
self-audit: PASS, configGrade A 96, pluginGrade A 100, readme gate passed.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
Chunk 2 of the disableBundledSkills GAP feature. Adds a conditional GAP check
that prescribes the `disableBundledSkills` lever — but only when the active
skill listing is measurably over budget (SKL's CA-SKL-002 overflow signal) and
the lever is un-pulled. It stays an opportunity, not noise.
Bundled skills (/code-review, /batch, /debug, /loop, /claude-api, …) live in the
CC binary, not on disk, so their exact cost is unmeasurable here — the finding
says so plainly, and frames the lever as zero-cost budget reclaim that leaves
the user's own skills untouched. CC 2.1.169+.
- Pure, exported bundledSkillsLeverFinding({leverPulled, aggregate}) → finding|null
(severity low, category token-efficiency, CA-GAP-NNN), wired into scan() via the
shared measureActiveSkillListing().
- Lever resolved via new isBundledSkillsDisabled(): env var + settings cascade
read directly, because discovery does NOT tag ~/.claude/settings.json (its
relPath lacks ".claude" when walked from the .claude root) — the dominant
user-scope location for this global preference would otherwise be missed.
- GAP scan() now reads HOME → existing GAP tests retrofitted to withHermeticHome
per the hermetic rule. Snapshots unchanged, contamination grep clean.
- 16 new tests (9 GAP, 7 lib). Suite 887 -> 903. README/CLAUDE.md document the
cross-scanner remediation; test counts synced. self-audit: PASS, configGrade
A 96, pluginGrade A 100, readme gate passed.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
Chunk 1 of the disableBundledSkills GAP feature. Moves the per-description cap,
aggregate budget constants, calibration note, and the enumerate-and-measure step
out of skill-listing-scanner into scanners/lib/skill-listing-budget.mjs — so SKL
(diagnoses overflow) and the upcoming GAP check (prescribes disableBundledSkills)
consume one budget definition instead of two divergent copies.
- New lib: assessSkillListingBudget (pure aggregate math) + measureActiveSkillListing
(HOME-scoped enumerate-and-measure wrapper).
- SKL delegates measurement; all finding strings kept byte-identical. 18/18 SKL
tests pass unchanged → behavior-neutral refactor.
- 12 new lib unit tests pin the budget contract. Suite 875 -> 887.
- README badge + CLAUDE.md test counts synced (self-audit --check-readme: passed).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
Fase 4 Items 2+3 (CC 2.1.114→181 gap-review). New orchestrated scanner
`skill-listing-scanner.mjs` (prefix SKL) flags every active skill whose
description exceeds the verified 1,536-char listing cap (CC 2.1.105, changelog
L1502). Past the cap, Claude Code silently truncates the description the model
reads to route skill invocation — dropping the trigger phrases at the tail.
HOME-scoped over all user + plugin skills via enumerateSkills (COL is the model).
- CA-SKL-001 (medium): description > 1,536 chars. Remediation folds in Item
2(b) — recommends disableBundledSkills + skillOverrides + trimming
(designvalg A: no standalone GAP-check, which would fire for nearly everyone).
- Designvalg B: v1 ships the verified cap ONLY. The aggregate 2%-of-context
listing budget is deferred — it needs a context-window assumption that would
turn a verified fact into a guess (would carry a CALIBRATION_NOTE if added).
- Choice C: recognize the skillOverrides settings key (CC 2.1.129) in
KNOWN_KEYS. Left OUT of TYPE_CHECKS — the value is a per-skill object
(off/user-invocable-only/name-only), not a string; a 'string' check (as the
plan sketched) would create a NEW false positive. Verify-first deviation.
Registration: scan-orchestrator (13th scanner), humanizer (SKL → 'Wasted
tokens' + static/_default translations), scoring SCANNER_AREA_MAP (→ Token
Efficiency; no 11th area), README badge 12→13, CLAUDE.md (finding-id +
test-count), docs/scanner-internals.md, gap-matrix + plan status notes.
Snapshots reseeded hermetically (SEED_SNAPSHOT/UPDATE_SNAPSHOT): SKL entry with
0 findings in empty HOME, scanners_ok 11→12, claudeMdEstimatedTokens bump from
the CLAUDE.md edits flowing through the cascade. Contamination grep clean.
Suite 868/868 (856 baseline + 11 SKL + 1 skillOverrides). RED→GREEN logged
per cycle.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
The DIS scanner collapsed Tool(param) rules to the bare tool name, so
Agent(model:opus) deny + Agent(model:sonnet) allow (and the same for
WebFetch(domain:...)) were flagged as dead config — a false positive now
that CC 2.1.178 matches Tool(param:value) and 2.1.172 adds domain rules.
The conflict-detector shared the blind spot from the other side: a
wildcard deny like WebFetch(domain:*) did not cover a
WebFetch(domain:good.com) allow, so a genuine cross-scope conflict was
missed (false negative).
New shared scanners/lib/permission-rules.mjs:
- parseRule / paramMatches (glob)
- dominates(deny, allow) -> DIS dead-allow (deny fully covers allow)
- rulesIntersect(a, b) -> CNF cross-scope conflict (match sets intersect)
DIS now delegates to dominates; conflict-detector :156 delegates to
rulesIntersect. A bare deny still covers all params, so true positives
are preserved (Bash deny + Bash(npm:*) allow still flagged).
Re-seeded the marketplace-medium snapshots: the false-positive CA-DIS
finding (Read(src/**) allow + Read(./.env) deny) is correctly gone. This
changes snapshot CONTENT only — envelope schema is unchanged, so --json
and --raw stay byte-stable.
Full suite: 837/837 green (+25). self-audit PASS, A(100)/A(97).
generateHealthScorecard signature: 2-arg → 3-arg (areaScores, opportunityCount,
options = {}). options.humanized=true renders friendlier title, grade-context
line per overall grade, and rephrased opportunity line. options.humanized=false
(or 2-arg call) preserves v5.0.0 verbatim output for backwards-compat.
topActions also gets an optional options.humanized that swaps recommendations
through humanizeFinding lookup.
posture.mjs main():
--json → write JSON to stdout, suppress stderr scorecard
--raw → write JSON to stdout (byte-identical to --json), write v5.0.0
verbatim scorecard to stderr
default → humanized scorecard to stderr, no stdout
posture.test.mjs scorecard-prose assertions re-anchored to --raw mode (the
explicit v5.0.0 path) — Wave 0 audit only covered finding-title strings;
scorecard prose surfaces here for the first time.
Wave 3 / Step 6 of v5.1.0 humanizer.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Wave 1 / Step 3 of v5.1.0 plain-language UX humanizer.
scanners/lib/humanizer.mjs exports three pure functions:
- humanizeFinding(f) -> new finding object with translated
title/description/recommendation + three new fields
(userImpactCategory, userActionLanguage, relevanceContext).
- humanizeFindings(findings) -> mapped array.
- humanizeEnvelope(env) -> walks env.scanners[].findings.
Plus computeRelevanceContext(filePath) as a named export for
unit testing.
Field semantics:
- userImpactCategory: from scanner prefix per research/02 line 124
(Configuration mistake / Conflict / Wasted tokens / Dead config /
Missed opportunity / Other).
- userActionLanguage: from severity per research/02 line 134
(Fix this now / Fix soon / Fix when convenient / Optional cleanup
/ FYI).
- relevanceContext: deterministic file-path heuristic — looks for
/tests/fixtures/ or /test/fixtures/ substring (test-fixture-no-impact),
*.local.* basename (affects-this-machine-only), defaults to
affects-everyone. No subprocess, no network.
Lookup order per scanner: static[title] -> patterns regex match ->
_default -> fall through to original strings (when scanner prefix
absent).
Original id, scanner, severity, file, line, evidence, category,
autoFixable, and optional details are preserved exactly. Pure —
verified by deepEqual of input before/after.
Test (32 cases): purity, field preservation across all paths,
known/unknown scanner handling, all 5 severities, all 6 categories,
relevance heuristic for 4 path types, envelope walking, ANSI-free
guarantee. All pass.
Regression: 689/689 tests (657 + 32 new = 54 new across Wave 1).
Project: .claude/projects/2026-05-01-config-audit-ux-redesign/
Wave 1 / Step 2 of v5.1.0 plain-language UX humanizer.
scanners/lib/humanizer-data.mjs exports TRANSLATIONS keyed by
scanner prefix (CML, SET, HKV, RUL, MCP, IMP, CNF, GAP, TOK, CPS,
DIS, COL, PLH). Each scanner has:
- static: exact-title -> {title, description, recommendation}
- patterns: array of {regex, translation} for template-literal titles
- _default: graceful fallback for unknown findings
Architectural change vs. plan: keys translations by exact scanner
title (not finding ID). Reason: finding IDs are sequence-based
(global counter in lib/output.mjs:34), not stable per finding-type
— two runs can produce different IDs for the same logical issue.
Title strings ARE stable (defined as string literals or template
patterns in the scanner source).
Translations follow research/03 SR-1..SR-17:
- active voice, second person, present tense
- sentences <= 25 words
- tier1 absolute prohibitions and tier3 domain jargon are kept out
of prose
- tier1/tier3 terms are permitted inside `backtick spans` (code
references like filenames and field names) — established
technical-doc convention
Test (12 cases): all 13 scanners covered; every static and pattern
entry has the 3 required fields; tier1 and tier3 forbidden-word
checks pass (with backtick-span exclusion); reference-stable
imports. All pass.
Regression: 657/657 tests (645 + 12 new).
Project: .claude/projects/2026-05-01-config-audit-ux-redesign/
Wave 1 / Step 1 of v5.1.0 plain-language UX humanizer.
tests/lint-forbidden-words.json defines the SC-3 forbidden-words
vocabulary used by the lint runner (Wave 4 / Step 8) and the
humanizer-data translation guard (Wave 1 / Step 2).
- Tier 1: 19 absolute prohibitions (failure if matched in default
output) — sourced from Microsoft Writing Style Guide, Federal
Plain Language, GOV.UK, Google Developer Style, Apple HIG.
- Tier 2: 24 strong-avoidance terms (warning if matched) — same
sources plus Mailchimp.
- Tier 3: 12 domain-specific jargon terms (failure if matched in
default output, allowed in --raw and --json paths) — sourced
from research/03 jargon table.
Counts diverge from plan.md (18/21/11) — JSON tracks the brief's
verbatim lists at research/03 lines 200-202 plus tier3 hook entry
from the brief's table. Plan revision noted in audit-doc.
Test: 10 cases verifying parse, count, schema completeness, spot
checks per tier, no cross-tier duplicates. All pass.
Regression: 645/645 tests (635 + 10 new).
Project: .claude/projects/2026-05-01-config-audit-ux-redesign/
Two MCP enumeration paths in readActiveMcpServers now pass kind='mcp'
to estimateTokens with optional toolCount derived from def.tools array
(populated when callers cache MCP discovery — Step 14 wires that up).
Hook callers keep kind='item' (no schema overhead).
Visible effect: every active MCP server jumps from estimatedTokens=15
to >= 500 (or higher when toolCount is known). The whats-active output
and TOK hotspots now reflect actual MCP cost.
Tests: assert mcpServers[].estimatedTokens >= 500 in fixture.
Replace count-based pass-rate with severity-weighted penalty:
- penalty = sum(count[s] * WEIGHTS[s])
- maxBudget = max(10, findingCount * 4)
- passRate = max(0, 100 - penalty / maxBudget * 100)
A few lows no longer crater an area's grade; a single high or critical
consumes a large fraction of budget. Mirrors the operator intuition that
severity, not count, is the signal.
BREAKING (intentional): scoring semantics differ from v4 for non-clean
configs. Add scoringVersion: 'v5' to the returned struct so consumers
can detect the version. baseline-all-a remains all-A (no critical/high
on that fixture).
Tests: +6 cases for severity weighting; existing "many findings" test
updated to use highs (where v5 still drops the grade as expected).
Promote WEIGHTS const to named export with Object.freeze for downstream
use in scoring.mjs (severity-weighted scoreByArea, F3).
Tests: +2 cases asserting WEIGHTS shape.
New read-only command that shows everything Claude Code actually loads for a
given repo — plugins, skills, MCP servers, hooks, CLAUDE.md cascade — with
source attribution (user/project/plugin) and rough token estimates. Helps
identify candidates for disabling without guessing.
Added:
- scanners/lib/active-config-reader.mjs — pure async helper: readActiveConfig,
detectGitRoot, walkClaudeMdCascade, readClaudeJsonProjectSlice (longest-prefix
matching for .claude.json projects), enumeratePlugins, enumerateSkills,
readActiveHooks, readActiveMcpServers, estimateTokens (markdown 4 c/tok,
json 3.5 c/tok, frontmatter cap 150 tokens, item flat 15)
- scanners/whats-active.mjs — thin CLI shim: --json, --output-file, --verbose,
--suggest-disables
- commands/whats-active.md — renders tables via Read tool; honors UX rules
- tests/lib/active-config-reader.test.mjs — 36 tests, all green (integration
fixture built in tmpdir with fake HOME, .claude.json prefix matching,
plugin discovery, hook/MCP merge from all scopes)
Verified:
- Performance budget: <2s wall-clock (smoke test: 102ms on real repo)
- Token estimates within ±20% of hand-computed values
- Read-only: no writeFile/mkdir/unlink in production code
- Self-audit: Plugin Health scanner reports 0 findings (Grade A)
- Full test suite: 522 tests, 512 pass (10 pre-existing conflict-detector
failures on main — unrelated to this change, reproducible on clean HEAD)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add /ultraresearch-local for structured research combining local codebase
analysis with external knowledge via parallel agent swarms. Produces research
briefs with triangulation, confidence ratings, and source quality assessment.
New command: /ultraresearch-local with modes --quick, --local, --external, --fg.
New agents: research-orchestrator (opus), docs-researcher, community-researcher,
security-researcher, contrarian-researcher, gemini-bridge (all sonnet).
New template: research-brief-template.md.
Integration: --research flag in /ultraplan-local accepts pre-built research
briefs (up to 3), enriches the interview and exploration phases. Planning
orchestrator cross-references brief findings during synthesis.
Design principle: Context Engineering — right information to right agent at
right time. Research briefs are structured artifacts in the pipeline:
ultraresearch → brief → ultraplan --research → plan → ultraexecute.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
