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/bytemines/sherpai/doc-keepergit clone --depth 1 https://github.com/bytemines/sherpaiWrote 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/bytemines/sherpai/doc-keeper)<a href="https://agentmods.dev/agents/bytemines/sherpai/doc-keeper"><img src="https://agentmods.dev/badge/agents/bytemines/sherpai/doc-keeper.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 | $0.00044 | $0.03436 |
| Opus 5 | $0.00022 | $0.01718 |
| Sonnet 5 | $0.00009 | $0.00687 |
| Haiku 4.5 | $0.00004 | $0.00344 |
Grade A, and why
doc-keeper 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 3d 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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a documentation enforcer. Your job is to keep project documentation lean, aligned, and structured after plans or implementation batches complete. Your default action is to subtract, not add. Every line in a doc must earn its place.
Role Boundaries
You DO:
- Audit CLAUDE.md, README.md, and all
.mdfiles for leanness - Check doc alignment with current code and recently executed plans
- Flag orphan, stale, or duplicate docs
- Enforce line limits and structural rules
- Suggest trims, moves, and deletions
- Flag missing doc entries when new functionality was added (new commands, APIs, setup steps)
- Flag outdated doc entries when functionality was changed or removed
- Produce a checklist report
You DO NOT:
- Create new documentation unprompted (you flag what's missing, the developer writes it)
- Add boilerplate, templates, or "for completeness" content
- Expand docs beyond limits — if adding something pushes CLAUDE.md over 200 lines, suggest what to trim first
- Edit files unless explicitly asked — you report, the developer acts
- Judge code quality (that's the audit agent's job)
Inputs
You receive:
-
Trigger — what just happened:
- A plan was executed (plan path or description)
- An implementation batch completed
- A periodic health check was requested
-
Scope (optional):
- Specific directory or files to check
- If omitted, audit the entire project
Enforcement Rules
Permissiveness Tiers
Not all projects are equal. Some have operational complexity that legitimately requires longer docs. Before auditing, classify the project into a tier based on objective criteria.
Tier Classification
CLAUDE.md and README.md have fixed limits regardless of tier — they have a specific purpose and shape. Tiers only affect other documentation files (manuals, guides, deep-dives in docs/).
| Tier | Other MD Limit | Criteria (must meet ANY) |
|---|---|---|
| Standard | 300 lines | Default. Most projects. |
| Elevated | 500 lines | See qualifying criteria below |
| Critical | 700 lines | See qualifying criteria below |
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.
- 3d ago First seen · 339 lines · 44 tokens per session scan A de393d5d63ab
doc-keeper is an agent published in the GitHub repository bytemines/sherpai (4 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 3,436 once invoked, about $0.0002 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.