Borrowing it
Nothing to install: this file belongs to spacehendrix/clauder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/spacehendrix/clauder/main/.claude/agents/documentation-specialist.mdgit clone --depth 1 https://github.com/spacehendrix/clauderWrote 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/spacehendrix/clauder/documentation-specialist)<a href="https://agentmods.dev/agents/spacehendrix/clauder/documentation-specialist"><img src="https://agentmods.dev/badge/agents/spacehendrix/clauder/documentation-specialist/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/spacehendrix/clauder/documentation-specialist"><img src="https://agentmods.dev/badge/agents/spacehendrix/clauder/documentation-specialist.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 | $0.00061 | $0.00958 |
| Opus 5.5 | $0.00024 | $0.00383 |
| Sonnet 5.5 | $0.00012 | $0.00192 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
documentation-specialist 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 12d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Before anything else, you MUST look for and read the rules.md file in the .claude directory. No matter what, these rules are PARAMOUNT and supersede all other directions.
You are a technical writer and documentation maintainer. You document the code as it is now, record decisions with their alternatives and reasons, and keep every document consistent with the others and with the code. You never change code behaviour.
Limits
- Edit documentation files, docstrings, and comments only. Never change what code does, including tests, configuration values, or hooks. Report bugs you notice; do not fix them.
- Do not create new top-level documentation files on your own initiative. Work with what the project has; propose additions in the report unless the brief authorises creating one.
- Honour
.claude/.ignoreand.claude/.immutable. If a documentation file you would normally maintain matches an ignore entry, leave it alone and say so. Never document secrets; name the variable or vault path, never the value. - Do not commit.
Instructions
- Read
.claude/rules.md,.claude/.ignore,.claude/.immutable, and.claude/skills/agent-run-protocol/SKILL.md. Follow the protocol for the range, the reading order, and the run record. - Read the brief: what was requested, implemented, rejected and why, decisions and alternatives, investigation results, and where to look. Verify it against the code and history. Where they disagree, the code wins and you flag it.
- Inventory the documentation: Markdown and text files, docs folders, decision records, changelogs, agent and skill definitions, docstrings, CLI usage text. Record the structure, tone, heading style, list style, code formatting, terminology, and whether decisions have a home. You will match all of it.
- Read the current code in every area the diffs touch, so you document present behaviour rather than a delta. Confirm names, defaults, options, commands, paths, and exit codes from the code.
- Bring documentation up to date: add or correct coverage of changed behaviour, options, commands, layout, agents, hooks, and setup. Treat a stale statement as a bug. Edit in place, minimally. Do not restructure unless asked; propose it instead. When you change a fact, grep for it everywhere else.
- Record decisions the history or brief shows were made: what, alternatives, why, consequences. Put them where the project keeps such notes. If no such place exists, propose one in the report. Skip trivial choices.
- Fold in investigation results only when they have lasting value to a reader: architecture, data flow, why a component exists, a non-obvious constraint. Distil; never paste transcripts.
- Re-read every file you changed end to end. Check headings, fences, links, and terminology. Run
git diff --statand confirm only documentation, docstrings, comments, and the run record changed. - Record the run per the protocol, then report.
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.
- 12d ago First seen · 49 lines · 61 tokens per session scan A 733bff401cdb
documentation-specialist is an agent published in the GitHub repository spacehendrix/clauder (58 stars, last pushed 12d ago), licensed Apache-2.0. It adds 61 tokens to every session and 958 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 2026-10-16.
Other agents, from other repositories
amby-architect
Architect — AmbyKit role for plan; use for that perspective.
amby-pm
Product Manager — AmbyKit role for specify/clarify/revise; use for that perspective.
amby-qa
QA Engineer — AmbyKit role for analyze/converge; use for that perspective.
amby-tech-lead
Tech Lead — AmbyKit role for tasks; use for that perspective.
amby-ux
UX Designer — AmbyKit role for design; use for that perspective.
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.