Syklus 2 of Fase 4 Items 2+3. Flags when the sum of active skill
descriptions exceeds the listing budget (~2% of context, CC 2.1.32).
Design (operator-confirmed "fact-first, 200k anchor"):
- low severity (estimate) vs medium for the verified 1,536-char cap
- each description counted up to the 1,536 cap (what actually loads in
the listing) — avoids double-counting the tail CA-SKL-001 flags
- fires when sum > 2% x 200k = 4000 tok; evidence leads with the measured
sum + a calibration note that the budget scales 5x on 1M-context models
- aggregate emitted after the per-skill loop so the common case reads
001=cap, 002=aggregate (finding IDs are a sequential counter, not stable
semantic IDs — tests match on title, never NNN)
Also:
- tailored humanizer static entry for the aggregate title
- fix latent HOME leak in posture-grade-stability.test.mjs: it spawned
posture.mjs without hermeticEnv(), so a real ~/.claude leaked HOME-scoped
SKL/COL findings into the baseline grade (Token Efficiency A->B). Now
isolated like the 8 other CLI-spawning tests.
- docs sync: test count 868->875, scanner-internals, gap-matrix, plan status
Suite 875/875, no snapshot drift, self-audit clean.
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
`.mcp.json` has no per-server `trust` key — verified 2026-06-18 against
code.claude.com/docs/en/mcp + /settings. MCP server approval is
dialog/settings-based (enableAllProjectMcpServers / enabledMcpjsonServers /
disabledMcpjsonServers), never a JSON field. The scanner's "Missing trust
level" (CA-MCP-001, medium) and "Invalid trust level" (high) were false
positives flagging a field that does not exist.
- scanner: delete both trust checks + VALID_TRUST_LEVELS; drop `trust` from
VALID_SERVER_FIELDS so a stray `trust` is now flagged as an unknown field
- humanizer: remove the two trust-level entries
- knowledge (5 files): point to the real approval mechanism, not a trust field
- fixtures: scrub `trust` (incl. the invalid "local" in optimal-setup)
- tests: flip assertions (no trust-level finding; stray trust -> unknown
field) + add knowledge-staleness re-freeze guards
- snapshots: reseed (marketplace-medium .mcp.json -8 tokens, hermetic)
- gap-matrix: mark the trust verify-first item DONE
Suite: 853/853 green.
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).
Step 8 of v5.1.0 humanizer Wave 4. Adds tests/lint-default-output.mjs
runner and tests/scanners/lint-default-output.test.mjs wrapper that
exercise SC-3 against the 6 prose CLIs (scan-orchestrator, posture,
token-hotspots-cli, plugin-health-scanner, drift-cli, fix-cli) running
in default (humanized) mode against tests/fixtures/marketplace-medium.
Lint scope is stderr only — JSON envelope keys ("scanner", "severity")
are structural, not prose. Humanized prose fields embedded inside JSON
are already covered by tests/lib/humanizer-data.test.mjs tier1/tier3
checks. Code references inside backticks pass the lint
(stripBacktickSpans) so technical identifiers can appear when wrapped.
Default-mode prose fixes to land lint at zero violations:
- scan-orchestrator: top banner switches to "Config-Audit v2.2.0" and
per-scanner progress wraps "[XXX] Label" in backticks. --raw and
--json paths preserve the v5.0.0 verbatim banner via new
opts.humanizedProgress flag on runAllScanners.
- plugin-health-scanner: top banner switches to "Plugin Health v2.1.0"
in default mode; --raw/--json keep "Plugin Health Scanner v2.1.0".
- scoring.mjs generateHealthScorecard humanized branch: area names
(CLAUDE.md, Hooks, MCP, Settings, Rules, Imports, Conflicts, Token
Efficiency, Plugin Hygiene) are wrapped in backticks; dot-padding
compensates so column alignment matches v5.0.0 layout.
- posture / drift-cli / fix-cli: thread humanizedProgress flag through
their runAllScanners calls so default mode emits humanized progress
and --raw/--json preserve the v5.0.0 stderr snapshot.
Test infrastructure only — user-facing docs land in Wave 5/6 once
commands and agents consume the humanized payload.
Tests: 735 to 736 (+1 SC-3 wrapper). Full suite passes.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
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/
New COL scanner detects skill-name collisions across plugins and
between user-level skills (~/.claude/skills/) and plugin-bundled
skills. Skill identity is the directory basename — matches how
enumerateSkills resolves names.
Detection rules (per docs/v5-namespace-research.md, confidence: medium):
- Plugin-vs-plugin same skill name → severity low (CA-COL-001)
- User-vs-plugin same skill name → severity medium (CA-COL-001)
- Plugin-vs-built-in collisions: out of scope for v5.0.0 (insufficient
verification — recorded for v5.0.1 follow-up).
Findings carry details.namespaces array with {source, name, path} for
every conflicting source — supports per-collision reporting downstream.
output.mjs: finding() helper now passes through optional `details`
field (scanner-specific structured payload).
scoring.mjs: COL → "Plugin Hygiene" (new area, 10 total). Posture test
updated from 9 → 10 area scores.
.gitignore: docs/v5-namespace-research.md is local-only (Step 22a
research output, gitignored per plan).
Fixture collision-plugins/fake-home/ has user skill `review` colliding
with plugin-a + plugin-b's `review` (medium severity), plus plugin-c's
unique `summarize` (no collision).
[skip-docs] reason: v5 plan fences off README/CLAUDE.md badge updates
to Session 5; Forgejo pre-commit-docs-gate hook requires this tag.
Tests: 617 → 625 (+8).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
New DIS scanner detects tools that appear in BOTH permissions.deny
and permissions.allow within the same settings.json file. The deny
list wins, so allow entries are dead config but still load on every
turn and confuse intent.
Tool identity = bare name (everything before "("). `Bash(npm:*)` and
`Bash` are treated as the same tool, so a deny on `Bash` flags any
`Bash(...)` allow entry.
Severity: low. Wired into scan-orchestrator + scoring (area: Settings).
Fixture denied-tools-in-schema has Bash in both arrays; healthy-project
serves as the negative case.
[skip-docs] reason: v5 plan fences off README/CLAUDE.md badge updates
to Session 5; Forgejo pre-commit-docs-gate hook requires this tag.
Tests: 611 → 617 (+6).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
New CPS scanner walks CLAUDE.md cascade and flags volatile content
between lines 31 and 150 — the cache-prefix window beyond TOK Pattern
A's top-30 territory. Volatile content anywhere in the cached prefix
forces a fresh cache write from that line down on every turn.
Volatile-pattern set extends TOK Pattern A with:
- shell-exec lines (! prefix) — common in CLAUDE.md to inject git/date
- ${VAR} substitutions — vary per-shell, defeat cache reuse
Severity: medium per finding. Skips lines 1-30 to avoid duplicating
Pattern A's range; CPS' value is in the 31-150 zone.
Wired into scan-orchestrator + scoring SCANNER_AREA_MAP. CPS shares
the "Token Efficiency" area with TOK; scoreByArea now deduplicates by
area name and combines counts across scanners contributing to the
same area, so the 9-area scorecard contract holds.
Fixtures volatile-mid-section/{volatile-line-60, volatile-line-200}
verify both positive (line 60) and out-of-window (line 200) cases.
[skip-docs] reason: v5 plan fences off README/CLAUDE.md badge updates
to Session 5; Forgejo pre-commit-docs-gate hook requires this tag.
Tests: 604 → 611 (+7).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
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>
