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/automagik-dev/genie/docsnpx skills add automagik-dev/genie --skill docsgit clone --depth 1 https://github.com/automagik-dev/genieWhat 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 | $0.00019 | $0.00705 |
| Opus 5 | $0.00010 | $0.00352 |
| Sonnet 5 | $0.00004 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00071 |
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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs — Documentation Generation
Runtime syntax: invoke the plugin copy through the active runtime's owner-qualified skill selector; use a bare selector only when intentionally selecting a user-tier copy (a separately installed personal copy; Genie no longer seeds this tier). Cross-skill prose below uses bare names as portable semantic routes; the orchestrator resolves the selector for the active runtime.
Audit existing documentation, fill gaps, and validate every claim against actual code. Standalone or as part of work.
When to Use
- Undocumented modules, APIs, or workflows; docs referencing removed features
- A wish deliverable includes documentation
- Code just changed in ways existing docs describe (e.g. after
workcompletes)
Surfaces
| Type | Location | Purpose |
|---|---|---|
| README | README.md, */README.md |
Overview, setup, usage |
| AGENTS.md | AGENTS.md, */AGENTS.md |
Agent conventions, constraints, commands, verification |
| CLAUDE.md | CLAUDE.md, */CLAUDE.md |
Conventions, commands, gotchas for agents |
| API docs | docs/api/, inline JSDoc/TSDoc |
Contracts, request/response schemas |
| Architecture | docs/architecture.md, ARCHITECTURE.md |
System design, data flow |
| Inline | JSDoc, TSDoc, docstrings | Function/class/module docs |
AGENTS.md is the governing agent instruction surface. CLAUDE.md remains evidence of repository intent when present; keep both current when the project has both files.
Flow
- Audit — map what exists across the surfaces above.
- Diff against code — find missing, stale, or wrong claims; governing
AGENTS.mdaccuracy first. - Generate — fill gaps in the project's existing documentation style.
- Validate — every referenced path exists, every API matches, every described behavior is real.
- Report — created/updated files with per-claim validation results.
Dispatch
Runs as a subagent (native runtime): the dispatching agent issues an native delegation surface call with a curated brief — scope (which docs, which change triggered the audit), the code areas to validate against, and the expected report shape.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 48 lines · 19 tokens per session scan A 17c768be4841
docs is a skill published in the GitHub repository automagik-dev/genie (334 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 705 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
electron-pro
Expert in building cross-platform desktop applications using web technologies (HTML/CSS/JS) with the Electron framework.
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
pr-feedback
Fetches PR review feedback and inline comments, categorizes them, and presents options to the user. Use when the user asks to get, read, address, or fix review comments on a pull request.
stock-explorer
A Yahoo Finance (yfinance) powered financial analysis tool. Get real-time quotes, generate technical indicator reports (RSI/MACD/Bollinger/VWAP/ATR), summarize fundamentals, and run a one-shot report that outputs a text summary.