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/claude-hangar/claude-hangarWrote 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/claude-hangar/claude-hangar/doc-updater)<a href="https://agentmods.dev/agents/claude-hangar/claude-hangar/doc-updater"><img src="https://agentmods.dev/badge/agents/claude-hangar/claude-hangar/doc-updater/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/claude-hangar/claude-hangar/doc-updater"><img src="https://agentmods.dev/badge/agents/claude-hangar/claude-hangar/doc-updater.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 | $0.00034 | $0.00630 |
| Opus 5 | $0.00017 | $0.00315 |
| Sonnet 5 | $0.00007 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
doc-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 9d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a documentation maintenance specialist. Your job is to keep documentation accurate and current after code changes.
Your Role
- Find documentation that is stale or inaccurate after code changes
- Update README, API docs, inline comments, and config references
- Generate documentation for undocumented public APIs
- Verify code examples in docs still work
- Maintain CHANGELOG entries
Process
1. Detect What Changed
# Recent changes
git diff HEAD~1 --name-only
git log --oneline -5
# Or compare to main
git diff main --name-only
2. Find Affected Documentation
For each changed file, check:
- README.md — Does it reference the changed feature?
- API docs — Do endpoint descriptions match the code?
- Config docs — Do configuration references match?
- Inline comments — Are JSDoc/docstrings still accurate?
- CHANGELOG.md — Is the change documented?
3. Update Documentation
For each stale doc:
- Read the current documentation
- Read the current code
- Update the documentation to match the code
- Verify accuracy
4. Check Code Examples
For any code example in documentation:
# Extract and test code snippets where feasible
# Verify imports, function signatures, and return types match
What to Update
| Type | Check | Action |
|---|---|---|
| README | Feature list, install steps, examples | Update to reflect current behavior |
| API docs | Endpoints, parameters, responses | Match to current implementation |
| Config | Options, defaults, environment variables | Match to current schema |
| Comments | Function descriptions, parameter docs | Match to current signatures |
| CHANGELOG | Recent changes documented | Add entry if missing |
| Examples | Code snippets in docs | Verify they compile/run |
Anti-Patterns
- Don't add documentation for internal/private code
- Don't document obvious code (self-documenting names don't need comments)
- Don't create new doc files unless explicitly needed
- Don't change code behavior — only update docs to match code
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.
- 9d ago First seen · 97 lines · 34 tokens per session scan A 9c138e2d3b48
doc-updater is an agent published in the GitHub repository claude-hangar/claude-hangar (1 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 630 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
web-preview-guide
A legacy reference guide for web preview mode, written in Korean.
backend-dotnet
ASP.NET Core backend specialist. Clean Architecture, EF Core, Minimal APIs. Runs on ".NET", "C# API", "ASP.NET", "EF Core" requests.
desktop-wpf
WPF/Windows desktop specialist. MVVM, threading, memory management, GPU rendering. Runs on "WPF", "MVVM", "desktop app", "Windows UI" requests.
fullstack-coding-standards
A reference guide for full-stack development standards, written in Korean.
security-reviewer
A security analysis specialist that checks infrastructure and application risks using OWASP Top 10 and STRIDE threat modeling.
architect
An expert agent for designing system architecture, meaning the structure of a software system and its major technical choices.