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/juanmhidalgo/claude-pluginsWrote 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/commands/juanmhidalgo/claude-plugins/analyze-claude-md)<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/analyze-claude-md"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/analyze-claude-md/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/commands/juanmhidalgo/claude-plugins/analyze-claude-md"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/analyze-claude-md.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 | $0.00043 | $0.01180 |
| Opus 5 | $0.00022 | $0.00590 |
| Sonnet 5 | $0.00009 | $0.00236 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
analyze-claude-md 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 10d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze CLAUDE.md
Analyze a CLAUDE.md file against Anthropic's official best practices.
Analysis Criteria
<structure_analysis weight="25">
- XML tags present and consistent
- Clear hierarchy (nesting, priority attributes)
- Sections properly labeled (context, instructions, examples, references) </structure_analysis>
<conciseness_analysis weight="25">
- Token count vs. target range for project size
- No verbose explanations of basic concepts
- No long embedded code examples (50+ lines)
- No repetitive content </conciseness_analysis>
<content_quality_analysis weight="25">
- Essential sections present (context, directories, standards, commands)
- External references for complex content
- Persuasion principles for critical rules (Authority, Commitment, Social Proof)
- NO sensitive data (credentials, keys, connection strings)
- Actionable workflows defined </content_quality_analysis>
<memory_patterns_analysis weight="25">
- Uses imports (@path) for external content
- Modularization with
.claude/rules/*.md - Path-specific rules use YAML frontmatter </memory_patterns_analysis>
Token Targets by Project Size
<token_targets>
- Small (< 10K LOC): 800-1200 tokens
- Medium (10-50K LOC): 1200-2000 tokens
- Large (> 50K LOC): 2000-2500 tokens </token_targets>
Scoring
<score_ranges>
- 90-100: Excellent (minor tweaks only)
- 75-89: Good (some optimization opportunities)
- 60-74: Needs improvement
- 0-59: Poor (major restructuring required) </score_ranges>
Output Format
<output_structure>
CLAUDE.md Analysis Report
File: [path] Date: [current date] Score: [X]/100 ([Rating])
Metrics
- Lines: [count]
- Estimated Tokens: [count * 8]
- Target Range: [range for project size]
- Status: [within/above/below target]
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.
- 10d ago First seen · 185 lines · 43 tokens per session scan A 4930e4a6d2a8
analyze-claude-md is a command published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,180 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 commands, from other repositories
tldr
Re-apply TLDR rules for this turn (verdict first, no filler).
tldr-update
Update TLDR from GitHub and refresh installed agent hooks/skills/rules.
tldr-help
Quick reference card for tldr modes, slash commands, and triggers.
tldr-commit
Generate tldr-style commit message (verdict first, ≤50 char subject, why over what).
tldr-compress
Compress natural language files into TLDR format to save input tokens.
tldr-review
One-line TLDR PR review comments (verdict first, no filler).