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 skills/godshiba/genesis/docsnpx skills add godshiba/genesis --skill docsgit clone --depth 1 https://github.com/godshiba/genesisWhat 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 | $0.00109 | $0.00808 |
| Opus 5 | $0.00055 | $0.00404 |
| Sonnet 5 | $0.00022 | $0.00162 |
| Haiku 4.5 | $0.00011 | $0.00081 |
Grade A, and why
docs 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 2d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/genesis:docs — Curate the Documentation
Turns accumulated, scattered documentation into a clean structure where every doc has a place, a purpose, and a G4 wire that keeps it true — without losing knowledge and without surprising the user.
Preconditions
- Must be a git repository. Every move and deletion has to be revertible
with one command. If the directory is not a repo, offer
git initfirst and stop if declined. - Works with or without an existing GENESIS kit. Without one, suggest running
/genesis:initfirst (the registries are where absorbed knowledge lands); proceed standalone only if the user prefers — then absorbed knowledge goes into the best existing doc instead of registries.
Protocol
-
Analyze. For repos with more than ~5 doc files, dispatch this plugin's
doc-curatoragent (registered asgenesis:doc-curator) via the Agent tool — it reads everything so the main context does not have to — and relay its migration plan. For small doc sets, run the curator's procedure inline (read its agent file for the classification taxonomy, verdicts, and plan format; follow it exactly). -
Present the plan and get approval. Show the full migration table (doc, class, verdict, destination), the registry entries to be seeded, and the drafts for missing docs. Use AskUserQuestion: approve all / approve with exclusions / cancel. Never execute an unapproved plan. If the user excludes items, execute only the remainder.
-
Execute, in this order:
- Seed registries with absorbed knowledge (DECISIONS/ISSUES/LANDMINES entries citing their source doc).
git mvfor every move and archive — never delete-and-recreate, so history follows the file.- Apply rewrites (stale claims corrected, with the code evidence the curator cited).
- Write the new docs from the approved drafts.
- Delete only
junk-verdict files and absorbed sources the plan marked for deletion. - Update
docs/registry/FILES.mdwith a row for every doc in the final structure, and extend the CLAUDE.md doc-sync map (G4) so each living doc has an owner area — this is what prevents the cleaned structure from rotting again.
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.
- 2d ago First seen · 66 lines · 109 tokens per session scan A a9042ca863a7
docs is a skill published in the GitHub repository godshiba/genesis (2 stars, last pushed 2mo ago), licensed MIT. It adds 109 tokens to every session and 808 once invoked, about $0.0005 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 skills, from other repositories
sql-reporting
Conventions and review steps for writing analytics SQL against the warehouse. Use whenever the task involves querying tables, building a report, or aggregating metrics.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
verify-security
安全校验关卡。自动扫描代码安全漏洞，检测危险模式，确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。.
development
开发语言能力索引。Python、Go、Rust、TypeScript、Java、C++、Shell。当用户提到编程、开发、代码、语言时路由到此。.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
n8n:human-like-code-review
Reviews a GitHub pull request like a thoughtful human reviewer and writes the feedback to a markdown file. Prioritizes context, architecture fit, solution complexity, bugs, security edge cases, and missing tests. Use when given a PR URL to review, or when the user says /human-like-code-review.