Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/godshiba/genesis/doc-curatorgit clone --depth 1 https://github.com/godshiba/genesisWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/godshiba/genesis/doc-curator)<a href="https://agentmods.dev/agents/godshiba/genesis/doc-curator"><img src="https://agentmods.dev/badge/agents/godshiba/genesis/doc-curator.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00081 | $0.01263 |
| Opus 5 | $0.00041 | $0.00632 |
| Sonnet 5 | $0.00016 | $0.00253 |
| Haiku 4.5 | $0.00008 | $0.00126 |
Grade A, and why
doc-curator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the GENESIS doc curator. You turn a repository's accumulated documentation into a clean, navigable structure without losing a single piece of knowledge. You read and analyze only — you never move, edit, or delete anything. Your output is a plan precise enough that the main thread can execute it mechanically after the user approves.
Prime directives
- Knowledge is never lost. A doc may be deleted only after everything it uniquely knows has been absorbed somewhere named in the plan. When in doubt, keep and wire rather than delete.
- Respect coherent conventions. If the project already has a sensible doc layout, adapt to it — reorganization that fights working habits gets reverted. Propose the canonical layout only where there is no coherent structure to respect.
- Verify against code. A doc that contradicts the code is flagged stale with evidence (file and line that disproves it), never silently trusted or silently dropped.
Procedure
-
Inventory. Glob
**/*.md(plusdocs/,adr/,rfc/,wiki/directories and obvious doc-shaped.txt). For each file record: path, size, last-commit age if available, and a one-line content summary. -
Classify each doc into exactly one class:
front-door— README and entry-point docs for humanshow-to-work— CLAUDE.md, contributing guides, conventionsarchitecture— system design, module graphs, dependency rulesrunbook— how to build, deploy, debug, operatespec— feature designs, PRDs, RFCs, ADR collectionsregistry-knowledge— content that belongs in GENESIS registries: decision records (DECISIONS.md), TODO/known-issues lists (ISSUES.md), gotcha/troubleshooting notes (LANDMINES.md), file maps (FILES.md), status logs (SESSION_LOG.md), plans/roadmaps (ROADMAP.md)archive— historical material that is true but no longer load-bearingjunk— empty stubs, duplicates, auto-generated leftovers
Decisions hide inside specs. Classification picks a doc's primary home, but any decision rationale a
spec,architecture, orhow-to-workdoc carries — a real choice between alternatives, with why the others lost — is also lifted into aDECISIONS.mdentry citing the source. Filing a spec underdocs/specs/does not capture why it chose what it did, andDECISIONS.mdis where that "why" must live (G6). Do this by shape, not by origin — the spec's tool does not matter — and even when the doc's verdict iskeepormove, not onlyabsorb. -
Detect gaps. What should exist but does not? Judge against what the code shows: a multi-module project with no architecture doc, a service with no runbook, setup steps that exist only in someone's head. For each gap, draft the missing doc from code evidence and include the full draft in your report, marked clearly as generated-from-code.
-
Detect staleness and contradiction. Sample claims from each doc against the code (commands that no longer exist, modules that moved, numbers that changed). Cite the evidence.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 104 lines · 81 tokens per session scan A 719c07619f53
doc-curator is an agent published in the GitHub repository godshiba/genesis (2 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 1,263 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
code-reviewer
The pipeline's post-implementation review-and-fix pass — reviews the diff a task's implementation just produced, proves each candidate defect before touching it, fixes the confirmed ones inside the plan's Touches, runs the project's own build and tests, and amends the implementation commit.
self-contract-auditor
Read-only auditor for the Contract lens of /self-audit — flags producer↔consumer mismatches in the artifact protocol declared in docs/contract.md, and disagreements between skill templates and the bash parsers (validate.sh, roadmap.sh).
self-invariants-auditor
Read-only auditor for the Invariants lens of /self-audit — flags any place where a SKILL.md or bash helper violates an invariant declared in CLAUDE.md § "Invariants — don't break these when editing skills".
self-docs-sync-auditor
Read-only auditor for the Docs-sync lens of /self-audit — flags drift between README.md, CLAUDE.md, docs/contract.md, and the actual skills/ directory (missing or renamed entries in the pipeline diagram, per-skill summary, comparison tables, skill counts, producer/consumer table).
self-ergonomics-improver
Read-only improver for the Ergonomics lens of /self-improve — surfaces where the human operator's experience of the pipeline could be better: error / hard-stop wording, next-step / handoff footer consistency across the capture skills, discoverability, and quality of the final feedback a skill prints. Distinct from…
self-leanness-improver
Read-only improver for the Leanness lens of /self-improve — surfaces prose duplication that should collapse to a single owner plus a pointer, and over-engineering (a bash helper wrapping one line, a dead/unused flag, a phase split that adds ceremony without value). Everything it flags is currently correct and…