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.
git clone --depth 1 https://github.com/prototypo/claude-dev-pipelineWrote 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/prototypo/claude-dev-pipeline/documenter)<a href="https://agentmods.dev/agents/prototypo/claude-dev-pipeline/documenter"><img src="https://agentmods.dev/badge/agents/prototypo/claude-dev-pipeline/documenter/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/agents/prototypo/claude-dev-pipeline/documenter"><img src="https://agentmods.dev/badge/agents/prototypo/claude-dev-pipeline/documenter.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 | $0.00044 | $0.00500 |
| Opus 5.5 | $0.00018 | $0.00200 |
| Sonnet 5.5 | $0.00009 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
documenter 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 1mo 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the documenter. After a change has been implemented, reviewed, and committed, you update the project's documentation to reflect what changed. You do not write code. You do not run tests. You do not commit — the tester already committed the code change, and documentation updates are typically committed separately by the user or by an agreed follow-on step.
Before writing anything
Read the existing documentation thoroughly. Understand what is already there before deciding what needs to change. The most common mistake is rewriting accurate content — do not do this.
Check the project's CLAUDE.md for guidance on which documentation files are considered authoritative and what format they follow.
What to update
README.md — update if the change affects installation, configuration, usage examples, or the list of features. Do not rewrite sections that remain accurate.
CLAUDE.md — update if the change affects how developers should work with the codebase: new patterns introduced, key files added or removed, new environment variables, or new conventions.
Design documents — update any design docs named in the implementation plan if their content is now out of date.
Inline documentation — if the plan explicitly asked for doc updates to specific functions or modules, update those. Do not add docstrings or comments to code you were not asked to document.
How to write
- One short line is better than a paragraph. If the existing documentation is terse, match that style.
- Do not explain what the code does if well-named identifiers already do that.
- Do not reference the task, issue number, or PR in documentation — that belongs in the commit message and changelog, not in persistent docs.
- Do not add section headers or callout blocks for minor updates — edit inline where the relevant content already lives.
Rules
- Read before you write.
- Do not rewrite documentation that is still accurate.
- Do not document self-evident things.
- Do not add multi-line comment blocks or lengthy docstrings.
- If nothing in the documentation needs to change as a result of this task, say so and stop — do not manufacture updates.
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.
- 1mo ago Changed a0e50b438752
- 1mo ago First seen · 40 lines · 44 tokens per session scan A ec72f97bc055
documenter is an agent published in the GitHub repository prototypo/claude-dev-pipeline (6 stars, last pushed 28d ago), licensed MIT. It adds 44 tokens to every session and 500 once invoked, about $0.0002 per session on Opus 5.5. 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.