Audit and repair Pharos documentation against the codebase. Use for documentation update passes, verified-doc drift, source-path/doc-sync failures, methodology/doc routing updates, or requests to verify docs without trusting existing prose.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Use for source-backed docs verification/repair and agent guidance/skill routing, not prose polish without evidence. Code and checked runtime data are truth; existing docs are hypotheses. Semantic auditors do not repeat CI-owned mechanical checks.
Select targeted failing doc check, code-change documentation update, broad semantic audit, methodology/version/timeline work, or agent/skill maintenance. Route likely source paths through docs/doc-ownership.json; inspect the matched source/local imports. Use node scripts/ci/pharos-change-contract.ts (--staged for staged changes) when assessing a change contract.
docs/doc-ownership.json, and Documentation Rules; read only the selected family/anchors, not all background docs./docs/ and README.md are the verified corpus, not committed planning archives. Durable process guidance belongs in existing verified docs.> **Agent navigation** block. Use matched section/offset reads, especially for docs/api-reference.md.src/app/**, src/components/**, src/lib/page-metadata.ts); API (shared/lib/api-endpoints/**, worker/src/routes/**, worker/src/api/**); cron (shared/lib/cron-jobs.ts, shared/lib/scheduled-runner-registry.ts, worker/src/cron/**); stablecoins (shared/data/stablecoins/coins/*.json, shared/lib/stablecoins/schema.ts); scripts/CI (package.json, scripts/**, .github/workflows/**); scoring (shared/lib/**, methodology changelogs and route sections). Use existing feature/process owners; update architecture only for structural changes and top-level guidance only when its contract changes.shared/lib/methodology-versions/constants.ts; Safety Score reads shared/lib/methodology-versions/current-version.json), the structured changelog under shared/data/methodology-changelogs/, the owning methodology document, and the relevant /methodology section when public explanation changes. Actual behavior changes update every target; prose correction of unchanged behavior needs no bump/changelog. Numeric versions have at most two decimal digits: v5.9 → v5.91 or v6.0, never v5.10 or v5.911.AGENTS.md; CLAUDE.md is the @AGENTS.md import. Durable process guidance belongs in linked docs/process/*.getVerifiedDocFiles(repoRoot) in scripts/lib/doc-files.mts, attach registry hints via reference path, and keep unmapped docs in scope. Reject missing selected paths and short expected inventories; no second filename roster or committed manifest. Partition disjoint coverage; record every skipped row/reason. Independent skeptics reopen non-empty findings and default to REJECTED; confirmed/revised source-backed findings alone enter synthesis. Without delegation, perform bounded discovery/skeptical reopening sequentially and disclose non-independent review. Remediation needs authorization (existing cohort approval remains valid), narrow writer scope and reopened evidence; parent owns de-duplication, final edits and validation.The assigned verifier runs relevant gates after writers finish; semantic reviewers return source evidence, not mechanical CI findings.
npm run check:verified-doc-links, npm run check:doc-sync; skills: npm run check:agent-skills.npm run check:generated-artifacts -- --only=api-reference,openapi,postman; broader generated work uses the registry-owned checks.Report docs changed, source files used as truth, actual verifier checks/outcomes or assigned checks, coverage/skips and independence for broad audits, unresolved questions, and intentionally omitted broader validation. Keep evidence in ignored scratch, not a new product-doc archive.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Review the retained annotation candidate queue and curate per-coin editorial history. Use weekly during active event periods, monthly otherwise, or on queue-health warnings; this does not restore the retired live chart overlay.
The English summary is being prepared. Showing the original description.
Generate a weekly changelog entry from git history, filtering operational noise and producing editorial summary, field notes, statistics, and a bounded commit manifest. Stops for review unless commit was explicitly requested.
The English summary is being prepared. Showing the original description.
Research and populate tracked stablecoin compliance sidecars for the U.S. GENIUS Act, EU MiCA, or both. Use when adding or auditing authorization, applicability, pathway, or disclosure evidence.
The English summary is being prepared. Showing the original description.
Use when adding, reviewing, squashing, deploying, or rolling back Pharos D1 migrations or schema cleanup.
The English summary is being prepared. Showing the original description.
Drain the Pharos Dependency Map coverage-audit queues into evidence-refreshed edges, reviewed target dispositions, or documented deferrals. Use monthly after weekly production dependency audits, after dependency coverage drops, or when reviewing adapter gaps, material unlinked slices, symbol leads, duplicate/split groups, or unverifiable published edges.
The English summary is being prepared. Showing the original description.
Update Pharos funding donations by reconciling inbound transfers, rejecting wallet self-activity and spam, pricing receipt-time value, and appending user-approved rows.
The English summary is being prepared. Showing the original description.