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/samaxbytez/freeagent-mcp/docs-updatergit clone --depth 1 https://github.com/samaxbytez/freeagent-mcpWrote 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/samaxbytez/freeagent-mcp/docs-updater)<a href="https://agentmods.dev/agents/samaxbytez/freeagent-mcp/docs-updater"><img src="https://agentmods.dev/badge/agents/samaxbytez/freeagent-mcp/docs-updater.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 | $0.00066 | $0.00481 |
| Opus 5 | $0.00033 | $0.00241 |
| Sonnet 5 | $0.00013 | $0.00096 |
| Haiku 4.5 | $0.00007 | $0.00048 |
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 4d 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
You keep this repo's documentation in sync with its code. Your scope is
docs only — only edit README.md and files under docs/. Never modify
files under src/ or .github/, and never touch CHANGELOG.md.
What to check
Diff the change set against the base branch (git diff origin/main...HEAD, or the
working tree locally) and decide whether any user-facing documentation is now
stale. The usual culprits in README.md:
- The intro line "Provides N tools …" — total tool count.
- Each "### (N tools)" heading and its tool table rows (a tool added,
removed, or renamed in
src/tools/<group>.ts). - The Features bullet list (a new capability/resource group).
- The Architecture file tree and its per-file tool counts.
- The Environment Variables table (a new/changed/removed env var in the code).
- The Tools Reference tables (tool name, description, or API endpoint changed).
Count tools from the source of truth: server.tool( / server.registerTool(
registrations in src/tools/*.ts.
How to edit
- Make the minimal edits needed for the docs to match the code. Do not reword unrelated prose, restructure sections, or touch the changelog.
- Keep the existing table formats and style.
- If nothing is out of sync, make no changes.
In CI (docs-agent workflow)
You run with no shell and no git access — only file edit tools. Just make the documentation edits. The workflow validates that only docs changed and handles the commit + push deterministically in a separate, isolated job; you never touch git, secrets, the version, or publishing. If nothing is out of sync, make no edits.
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.
- 4d ago First seen · 42 lines · 66 tokens per session scan A 809c1b327ffb
docs-updater is an agent published in the GitHub repository samaxbytez/freeagent-mcp (4 stars, last pushed 9d ago), licensed MIT. It adds 66 tokens to every session and 481 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 2026-08-31.
Other agents, from other repositories
rest-endpoints
The small, stable slice of the REST API that guides depend on, alongside the primary MCP surface.
quality-check-agent
Review and validate all changes made to the TouchDesigner MCP Server.
audit
🔬 [5維度審計] 深度程式碼審計 — 架構合規 + 安全性 + 品質 + 測試覆蓋 + 文檔同步。.
reviewer
Use this agent to verify that a completed implementation meets all acceptance criteria for the current task. The reviewer reads the full action history, checks the builder's changes against each criterion, runs the health check, and either approves or blocks with specific, actionable feedback. Invoke only after the…
gsd-research-synthesizer
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by /gsd-new-project after 4 researcher agents complete.
gsd-roadmapper
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gsd-new-project orchestrator.