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/optimize-claude-md)<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/optimize-claude-md"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/optimize-claude-md.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 5.1 | $0.00038 | $0.00833 |
| Opus 5 | $0.00019 | $0.00417 |
| Sonnet 5 | $0.00008 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
optimize-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 7d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize CLAUDE.md
Apply Anthropic's best practices to optimize CLAUDE.md structure, conciseness, and token efficiency.
Parse arguments
Path: $1, or auto-detect (./CLAUDE.md → ./.claude/CLAUDE.md).
Level: extract --level=X from $ARGUMENTS. Default: moderate. Valid values: conservative, moderate, aggressive.
For each level's full scope (what is/isn't changed), see @optimize-claude-md.references/levels-and-strategies.md.
Workflow
- Backup —
cp [original] [original].backup-[timestamp]. Show the backup path. Blocking. - Transform — apply optimizations at the chosen level. Track before/after metrics (lines, tokens).
- Preview — show metrics comparison, key changes list, 2–3 side-by-side examples, backup location.
- Confirm — ask the user: apply / cancel / save-as-new. Do NOT proceed without explicit confirmation. Blocking.
- Apply — write optimized content (or to
[original].optimized.mdif save-as-new), or delete backup if cancelled. - Post-optimization message — print metrics, next steps, backup-restore command.
For optimization-strategy details (XML structure target, conciseness moves, content enhancements, full success message, error handling), see @optimize-claude-md.references/levels-and-strategies.md.
Safety checks
Content preservation (blocking): before writing, ensure (1) all original info preserved, (2) no loss of project context, (3) no removal of critical rules, (4) XML tags properly closed, (5) token count is LOWER than original.
Sensitive data (blocking): if credentials, API keys, or connection strings are found — FLAG IMMEDIATELY, do NOT include in the optimized version, inform the user.
Already optimized: if analysis score > 85, inform the user and ask if they want to proceed anyway.
<critical_rules> NEVER write to the original file without creating a backup first. No exceptions.
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.
- 7d ago First seen · 84 lines · 38 tokens per session scan A d2b4cc28e24c
optimize-claude-md is a command published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 12d ago), licensed MIT. It adds 38 tokens to every session and 833 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.