plugin-health flagged "CLAUDE.md missing <commands|agents|hooks> section" regardless of
whether the plugin actually had that component — e.g. graceful-handoff (no commands/ or
agents/ dir) got two spurious medium findings. Same over-report class as the model-field fix.
Now gated on component presence (pluginShipsComponent): a section is required only if the
plugin ships that component (commands/ or agents/ with .md, or hooks/hooks.json). Across the 5
stable plugins this drops 12 spurious findings to 3 legitimate ones (graceful-handoff hooks,
ai-psychosis commands+hooks). New fixture plugin-section-coverage proves both directions.
Found via the marketplace-wide review. Suite 950/950, self-audit A/A, scanner count 13.
tests badge 949 -> 950.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
plugin-health-scanner required `model`+`allowed-tools` on commands and `model`+`tools`
on agents, plus `name` on commands. Per primary docs these are OPTIONAL:
- Commands/skills (code.claude.com/docs slash-commands): "All fields are optional. Only
`description` is recommended." `name` defaults to the directory name.
- Subagents (code.claude.com/docs sub-agents): "Only `name` and `description` are required";
`model` defaults to `inherit`, `tools` inherits all.
REQUIRED_COMMAND_FRONTMATTER -> [description]; REQUIRED_AGENT_FRONTMATTER -> [name, description].
This was over-reporting: every command without an explicit `model` got a spurious medium
finding (10 on the okr plugin alone). Found via the okr pilot review. Suite 949/949, self-audit
A/A, scanner count 13 (no new scanner).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
settings-validator now validates the autoMode block (auto-mode classifier
config). Structure (medium): autoMode must be an object whose only keys are
environment/allow/soft_deny/hard_deny, each a string array ("$defaults" is a
valid entry); flags not-an-object, unknown-subkey, not-string-array. Dead-config
(low): Claude Code does not read autoMode from shared project settings
(.claude/settings.json), so an autoMode block committed there has no effect —
keyed on file.scope === 'project'.
Both premises primary-source-verified (code.claude.com/docs/en/auto-mode-config).
The plan's "test per-file scope first" gate passed: ConfigFile already carries
scope. SET is in the orchestrator; SC-5 re-checked, byte-equal (snapshot fixture
has no autoMode). Fixtures force-added (.claude/ is gitignored).
Tests +5 (944->949). Scanner count unchanged (13). --json/--raw byte-stable.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
PLH now validates each entry of a plugin.json `skills` field (string|array):
every entry must resolve to an existing directory inside the plugin root.
One finding per bad entry (medium, plugin-hygiene), problem ∈ {non-string,
escapes-root, not-found, not-a-directory}. Mirrors `claude plugin validate`.
String|array normalized so a non-string top-level value is caught too.
Verifiseringsplikt: the plan's "CC suggests the parent directory" error text
is NOT in the primary docs — dropped. Only the four primary-source-verified
conditions are asserted (escape backed by the path-traversal rule).
Tests +3 (941->944). Scanner count unchanged (13). --json/--raw byte-stable.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
PLH now flags a plugin.json component-path key (commands/agents/outputStyles)
that replaces a default folder still present on disk — Claude Code stops
scanning that folder, so its contents are silently ignored (dead config).
Mirrors CC's /doctor & `claude plugin list` warning (v2.1.140+).
Field set pinned to the docs' "replaces" category only (Verifiseringsplikt,
code.claude.com/docs path-behavior-rules): skills is excluded (adds to the
default skills/ scan — both load) as are hooks/mcpServers/lspServers (own
merge rules); a custom path that addresses the default folder is not flagged.
Tests +5 (936->941). Scanner count unchanged (13). --json/--raw byte-stable.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
Commands are namespaced (/name:command), so a command name shared by two
differently-named plugins keeps both reachable — it is ambiguity, not a hard
conflict. The check now mirrors COL's plugin-vs-plugin skill finding: severity
LOW (was HIGH), category plugin-hygiene, COL-shaped details.namespaces, and a
group-first shape (one finding per command name listing every namespace, not
pairwise). It keys on the declared namespace (was folder basename) and fires
only across 2+ distinct namespaces — when plugins share a declared name, the
namespace-collision finding (medium) is the right signal, so this stays silent.
Removes the inaccurate "only one wins" humanizer entry. Adds fixtures
(duplicate-command-name; a shared command in duplicate-plugin-name's colliding
namespace) and 4 tests. Suite 932->936. self-audit A 97 / A 100, scanners 13.
Two plugins that declare the same `name` in plugin.json collapse into one
component namespace (/name:command, name:skill, agent "name"). Resolution
between two installed same-name plugins is undocumented, so one plugin's
commands/skills/agents are silently shadowed and unreachable. PLH now flags
this at medium severity, keying on the declared `name` (not folder basename,
via new declaredName on scanSinglePlugin) with a COL-shaped details.namespaces
payload. Name-less plugins are excluded from the collision map.
Search-first (code.claude.com/docs/en/plugins): plugin components are
namespaced by the declared name, so a plugin component can never shadow a
user/project one — only a same-name collision loses components. This refutes
the original "plugin vs user vs project shadowing" framing in the backlog.
Adds humanizer pattern, fixture (duplicate-plugin-name: 2 colliding + 2
name-less), and 3 tests. Suite 929->932. self-audit A 97 / A 100, scanners 13.
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
Add a char-based CML finding that mirrors Claude Code's own startup warning
("Large CLAUDE.md will impact performance (X chars > 40.0k)"). CC 2.1.169 scales
that threshold with the model's context window, so the finding anchors on the
conservative 200k window (we cannot observe the user's window; the anchor fires
earliest) and discloses the relaxed ~200,000-char figure at 1M context. MEDIUM
severity (token cost, not an adherence cliff — consistent with the v5.2.0 reframe).
Keyed on chars, not lines, so it is complementary to the existing 200/500-line
checks (which stay untouched): a file can be long by lines yet under budget (short
lines, e.g. large-cascade at 37k chars / 1024 lines), or short by lines yet over it.
Extract the shared 200k/1M context-window constants to scanners/lib/context-window.mjs
(single source of truth; skill-listing-budget.mjs now imports + re-exports them).
40.0k figure and context-window scaling verified against the CC changelog (2.1.169,
2026-06-08) and the live startup-warning text. +6 tests, new fixture large-claude-chars
(48,531 chars / 100 lines). Suite 918/918, self-audit PASS configGrade A 97.
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
`.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).
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>
Adds detectMcpToolBudget detection block in TOK scanner. Tiered severity
per project-local .mcp.json server based on toolCount:
- < 20: no finding
- 20-49: low
- 50-99: medium
- 100+: high
- null (manifest unparseable): low + "tool count unknown" message
Scoped to source==='.mcp.json' to keep findings actionable for the
audited path; plugin/user-level MCP servers are surfaced by the
manifest scanner (Step 19 / N2).
5 fixtures (mcp-budget/{14,25,60,120,unknown}-tools) use inline `tools`
arrays in .mcp.json — no node_modules needed for these tests.
Tests assert title+severity (not exact ID) since TOK IDs are sequential
per scan, not semantic per pattern.
[skip-docs] reason: v5 plan fences off README/CLAUDE.md badge updates
to Session 5; Forgejo pre-commit-docs-gate hook requires this tag on
feat commits without doc changes.
Tests: 586 → 593 (+7).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Filesystem counts are the source of truth; README badges parsed via
line-anchored substring (badge/<kind>-<N>-...). Emits readmeCheck object
with counts/badges/mismatches.
CLI: node scanners/self-audit.mjs --check-readme [--json]
API: runSelfAudit({ checkReadme: true }) → result.readmeCheck
Helper: checkReadmeBadges(pluginDir) for per-fixture testing
New fixture: readme-desynced/ (commands/foo + bar, README claims 1).
Note: alpha phase does NOT require result.readmeCheck.passed === true.
Self-test of real plugin currently fails (scanners 10 vs 9, tests 31 vs 543);
will be reconciled in Session 5 Step 28 (README sync).
582 → 586 tests, all green.
The mcp-tool-heavy fixture relies on node_modules/mcp-heavy/package.json
being committed so the v5 M1 tool-count detection test runs deterministically.
Add an unignore rule for tests/fixtures/**/node_modules/.
- New Pattern F in TOK: low-severity finding when SKILL.md description > 500 chars
- Scoped to discovery.files (project-local) — activeConfig.skills walk would
pull in user/plugin skills out of project scope
- New fixtures: skill-bloated (594-char desc) + skill-tight (46-char baseline)
574 → 576 tests, all green.
- New Pattern E in TOK: emits medium finding when activeConfig.claudeMd.estimatedTokens > 10_000
- Uses cascade tokens, file count, and calibration note as evidence
- New fixtures: large-cascade (37k bytes / 14475 cascade tokens) + small-cascade (5k baseline)
572 → 574 tests, all green.
Removes the v4 'void readActiveConfig' placeholder and wires the
active-config snapshot into the TOK scanner.
Per-turn behavior changes:
- Each enabled MCP server becomes its own hotspot entry (richer than
the parent .mcp.json file alone)
- total_estimated_tokens now includes MCP server cost
- result.activeConfig exposes a small summary
(claudeMdEstimatedTokens, mcpServerCount, pluginCount, skillCount)
Failures of readActiveConfig are non-fatal — the scanner falls back
to the discovery-only path used in v4.
Tests: +3 cases on the new tok-active-config fixture
(.mcp.json with 2 servers, CLAUDE.md, plugin skeleton).
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>
