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 skills add hex/claude-council --skill docs-updatergit clone --depth 1 https://github.com/hex/claude-councilWrote 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/skills/hex/claude-council/docs-updater)<a href="https://agentmods.dev/skills/hex/claude-council/docs-updater"><img src="https://agentmods.dev/badge/skills/hex/claude-council/docs-updater/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hex/claude-council/docs-updater"><img src="https://agentmods.dev/badge/skills/hex/claude-council/docs-updater.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00801 |
| Opus 5.5 | $0.00000 | $0.00320 |
| Sonnet 5.5 | $0.00000 | $0.00160 |
| Haiku 4.5 | $0.00000 | $0.00080 |
Grade A, and why
docs-updater 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 22d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Updater
Bring documentation in line with the code as it is now. Every behaviour claim must be checked against the code. No fact may disappear unless there is proof it is obsolete.
Scope
- List the pages or files in scope and the code changes they must reflect. If the task names only the code change, find the docs that mention the affected commands, flags, config keys, endpoints or errors.
- Read the project's docs conventions: style guide, frontmatter, link format, generated-docs tooling. If a page is generated, edit the generator or its source, never the output.
- Change no production code. If the docs reveal a code bug, report it.
Inventory before editing
For each page, list every fact it states before you rewrite it:
- commands, subcommands, flags, environment variables, config keys, defaults, allowed values, units;
- limits, timeouts, precedence rules, fallbacks, ordering, rate limits;
- permissions, auth, safety and destructive-action behaviour;
- setup requirements: versions, operating systems, dependencies, credentials;
- error messages, symptoms and recovery steps;
- examples, expected output, tables and links.
Give each fact one fate:
- keep: it stays on this page;
- move: name the destination page and section;
- delete: name the code, schema or --help output that proves it obsolete.
Find the source of truth
Check every behaviour-sensitive claim against the nearest authority:
- config: the schema, type definitions or parsing code;
- CLI: the command definitions and the real --help output;
- runtime behaviour: the implementing code and its tests;
- APIs: the handler code, the schema or contract tests.
Existing docs are secondary evidence only. Never infer a default, permission or timeout from a name or from the old text. Run the command or read the code. A reference table missing a public field, default or limit is a correctness bug, not a style issue.
Rewrite
- Open with what the reader can do and why the page exists.
- Put the recommended path before alternatives.
- Keep the common case in the main flow. Move exhaustive tables and rare detail to a reference page and link to it where it is needed.
- Keep one canonical place for each fact. Link rather than duplicate.
- Update examples so they run against the current code. Run them where you can and record which ones you ran.
- Write troubleshooting from observable symptoms.
- Leave no placeholder such as TODO, TBD or "see docs".
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.
- 22d ago First seen · 92 lines · 0 tokens per session scan A 84f1bb2c84a6
docs-updater is a skill published in the GitHub repository hex/claude-council (884 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 801 tokens. 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 2026-09-26.
Other skills, from other repositories
report-generator
Generate professional HTML/PDF investment reports with interactive visualizations.
gemini-file-analysis
Analyze files (PDFs, images, audio, video, large source files) via Gemini's multi-modal file analysis. Use when a file is too large for Claude's context or when the file is a non-text format requiring visual/audio understanding.
vault
Generate an Obsidian LLM wiki vault from a project's source code and any static documents in raw/.
rlm
This skill should be used when the user asks to "process a large file", "analyze document exceeding context", "use RLM", "recursive language model workflow", "chunk and analyze a file", "handle long context", or needs to work with documents too large to fit in the context window. Orchestrates the full RLM loop using…
research-archivist
Use this skill when the user asks to ingest, organize, archive, or update research source materials, wiki pages, evidence packs, or information packs.
gemini-prompting
Internal guidance for composing Gemini prompts for planning, research, diagnosis, and review tasks inside the Gemini Claude Code plugin.