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 tmj-90/gaffer --skill update-docsgit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/update-docs)<a href="https://agentmods.dev/skills/tmj-90/gaffer/update-docs"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/update-docs/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/tmj-90/gaffer/update-docs"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/update-docs.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 | $0.00064 | $0.00406 |
| Opus 5 | $0.00032 | $0.00203 |
| Sonnet 5 | $0.00013 | $0.00081 |
| Haiku 4.5 | $0.00006 | $0.00041 |
Grade A, and why
update-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 7d 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.
What it actually says
Update the docs
Bring documentation back in line with the code. Keep it accurate and matched to the repo's existing docs structure — don't spawn a parallel doc system.
Steps
- Find the source of truth and the docs that reference it. Identify what changed
(a route, a config key, a CLI flag, a schema) and locate every doc that describes it:
README,
docs/, API reference, changelog, inline examples. - Read the lore if the change touches a convention —
search_lore(Memory MCP) for docs/style conventions (changelog format, where API docs live, voice). - Update only what the change affects. Correct commands, signatures, payloads, and examples so they match the code exactly. Add a changelog entry in the repo's format if one exists. Don't rewrite unrelated sections.
- Verify the examples are real — run any documented command or sample request and confirm it produces what the doc claims. Fix drift you find.
- Evidence: the changed doc files and (where applicable) the command output proving an
example works. Then use the
record-evidenceskill (diff_summary) and submit for review.
Rules
- Docs must match the code exactly; verify commands and examples actually run.
- Edit existing docs in place; don't introduce a new docs framework or location.
- Keep scope tight — only the sections the change touches.
- Run on a branch (the
create-branchskill), never a protected branch.
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.
- 7d ago First seen · 34 lines · 64 tokens per session scan A 66afa62c6ab8
update-docs is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 64 tokens to every session and 406 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
bulwark-brainstorm
Role-based brainstorming with dual modes: --scoped (sequential Task tool, 5 roles) and --exploratory (Agent Teams peer debate, 4 roles). Use for feasibility assessment and idea validation.
plan-creation
Create structured implementation plans via a 4-role scrum team (Product Owner, Architect, Eng/Delivery Lead, QA/Critic) with optional Agent Teams peer debate mode.
anthropic-validator
Validates Claude Code assets (skills, hooks, agents, commands, MCP servers, plugins) against official Anthropic standards. Fetches latest docs dynamically and produces structured validation reports.
create-subagent
Generates single-purpose Claude Code sub-agents for use via the Task tool. Use when creating dedicated sub-agents, scaffolding agent definitions, or generating agents with diagnostics and permissions setup.
test-audit
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.
code-review
Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.