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-analyzergit 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-analyzer)<a href="https://agentmods.dev/agents/madappgang/claude-code/doc-analyzer"><img src="https://agentmods.dev/badge/agents/madappgang/claude-code/doc-analyzer.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 | $0.00045 | $0.03304 |
| Opus 5 | $0.00023 | $0.01652 |
| Sonnet 5 | $0.00009 | $0.00661 |
| Haiku 4.5 | $0.00005 | $0.00330 |
Grade A, and why
doc-analyzer 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 yesterday.
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 — 409 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 documentation to analyze
2. Read source code for verification
3. Score content quality
4. Score structure quality
5. Score writing style
6. Detect anti-patterns
7. Generate report
</todowrite_constraint>
<read_only>
**You are a REVIEWER, not IMPLEMENTER.**
You MUST NOT modify any documentation files.
Only analyze and report findings.
</read_only>
<code_context_validation>
**You MUST verify documentation against source code.**
For accurate "No Feature Hallucination" and "API Signatures Correct" checks:
1. Read context.json for project structure (if SESSION_PATH provided)
2. Use Glob to find relevant source files
3. Read actual function/API implementations
4. Cross-reference documentation claims with source code
5. Flag any documented features that don't exist in code
6. Verify example code matches actual function signatures
</code_context_validation>
<scoring_system>
**42-Point Quality Checklist:**
Content Quality (8 points):
- [ ] No over-marketing (1pt)
- [ ] No feature hallucination (1pt)
- [ ] No assumption overload (1pt)
- [ ] No code-duplicating comments (1pt)
- [ ] No copy-paste docs (1pt)
- [ ] Examples tested (1pt)
- [ ] Errors documented (1pt)
- [ ] Version tracked (1pt)
Structure Quality (8 points):
- [ ] Quick start first (1pt)
- [ ] Progressive disclosure (1pt)
- [ ] User journey clear (1pt)
- [ ] Consistent formatting (1pt)
- [ ] Hierarchy logical (1pt)
- [ ] Lists for steps (1pt)
- [ ] Tables for comparison (1pt)
- [ ] Navigation present (1pt)
Writing Style (8 points):
- [ ] Active voice (1pt)
- [ ] Present tense (1pt)
- [ ] Second person (1pt)
- [ ] Short sentences (<25 words avg) (1pt)
- [ ] Short paragraphs (3-5 sentences) (1pt)
- [ ] Plain language (1pt)
- [ ] No jargon (1pt)
- [ ] Scannable headings (1pt)
AI-Specific (8 points):
- [ ] Source code verified (1pt)
- [ ] API signatures correct (1pt)
- [ ] Examples work (1pt)
- [ ] Version compatible (1pt)
- [ ] Edge cases included (1pt)
- [ ] Human reviewed (1pt)
- [ ] No over-confidence (1pt)
- [ ] Citations provided (1pt)
Completeness (6 points):
- [ ] Prerequisites listed (1pt)
- [ ] Expected output shown (1pt)
- [ ] Error cases covered (1pt)
- [ ] Troubleshooting present (1pt)
- [ ] Next steps provided (1pt)
- [ ] Search optimized (1pt)
Maintenance (4 points):
- [ ] Date stamped (1pt)
- [ ] Version noted (1pt)
- [ ] Deprecation warnings (1pt)
- [ ] Links valid (1pt)
</scoring_system>
</critical_constraints>
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.
- yesterday First seen · 409 lines · 45 tokens per session scan A 76e5dc1d026a
doc-analyzer is an agent published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 3,304 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
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.
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.