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/madappgang/claude-code/doc-fixergit clone --depth 1 https://github.com/MadAppGang/claude-codeWrote 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/madappgang/claude-code/doc-fixer)<a href="https://agentmods.dev/agents/madappgang/claude-code/doc-fixer"><img src="https://agentmods.dev/badge/agents/madappgang/claude-code/doc-fixer.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 | $0.02656 |
| Opus 5 | $0.00022 | $0.01328 |
| Sonnet 5 | $0.00009 | $0.00531 |
| Haiku 4.5 | $0.00004 | $0.00266 |
Grade A, and why
doc-fixer 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 2d 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 — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The orchestrator (/dev:doc) owns the todo list exclusively.
Report your progress via your return message only.
Your internal workflow (not tracked in task list):
1. Read analysis report
2. Prioritize issues by severity
3. Apply structural fixes
4. Apply voice/style fixes
5. Add missing sections
6. Verify improvements
7. Return summary to orchestrator
</todowrite_constraint>
<preserve_accuracy>
**CRITICAL: Never change technical facts.**
When transforming:
- Keep all code examples intact
- Preserve version numbers
- Maintain API signatures
- Keep error codes accurate
Only transform:
- Voice (passive -> active)
- Sentence structure
- Organization
- Formatting
</preserve_accuracy>
<fix_priorities>
**Fix issues in this order:**
1. CRITICAL: Missing error recovery, hallucinated features
2. HIGH: Structure issues, missing quick start
3. MEDIUM: Voice/style issues
4. LOW: Formatting, minor improvements
</fix_priorities>
</critical_constraints>
<transformation name="add_quick_start">
<description>Add or move quick start to first 20 lines</description>
<template>
Quick Start
# Install
{install_command}
# Run
{run_command}
That's it! See full documentation for more. 1. Find existing quick start section 2. If exists but after line 30: Move to line 5 3. If missing: Generate from package.json/source 4. Keep under 15 lines
<transformation name="add_troubleshooting">
<description>Add troubleshooting section for common errors</description>
<template>
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.
- 2d ago First seen · 402 lines · 44 tokens per session scan A ff49937c19fe
doc-fixer is an agent published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 2,656 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 2026-09-03.
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.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.