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/extract)<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/extract"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/extract/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/extract"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/extract.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 | $0.00038 | $0.01181 |
| Opus 5.5 | $0.00015 | $0.00472 |
| Sonnet 5.5 | $0.00008 | $0.00236 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
extract 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 14d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Extraction
Safely extract code into a reusable unit.
What to extract: $ARGUMENTS
Phase 1: Understand the Context
- The code to extract (if not specified precisely)
- Where similar extractions live in this project
- Naming conventions for functions/classes/modules
- Test files that need updating
Phase 1.5: Conflict Check
<conflict_check> Extraction rewrites existing lines, so any open PR touching the same file will conflict. One call, before you clarify anything:
gh pr list --state open --limit 40 --json number,title,author,isDraft,updatedAt,files \
--jq '.[] | select(.files[].path | test("<source-file>|<destination-file>")) | {number, title, author: .author.login, isDraft, updatedAt}'
git status --porcelain -- <source-file> <destination-file>
Act on the result:
| Result | Action |
|---|---|
| No open PR, clean status | Proceed to Phase 2 |
| Uncommitted local edits | Tell the user; offer to commit or stash first |
| An open PR touches the file | Stop and surface it — PR number, title, author, age. Use AskUserQuestion: extract now and accept the conflict, extract a different piece, or wait for the PR to merge. Do not decide this silently |
| A PR calls the symbol you are moving but does not touch these files | Surface it too — the move merges clean and breaks that PR at runtime. Keep the old name as a shim, or wait |
gh missing or unauthenticated |
Say so and continue on the local check alone — do not report the file as clear |
</conflict_check>
Phase 2: Clarify Extraction
| Question | Impact if wrong | Default |
|---|---|---|
| Extract as function, class, or module? | Structure mismatch | Function if <50 lines |
| Placement - same file or new file? | Import complexity | Same file if related |
| Name for the extracted code? | Discoverability | [Suggest based on content] |
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.
- 14d ago Changed · +2 lines 8522b325e75f
- 23d ago Changed · -24 lines 525277dd4493
- 1mo ago Changed · +29 lines d689f923a9a4
- 1mo ago First seen · 160 lines · 38 tokens per session scan A 7a9be3e0e0c2
extract is a command published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 1,181 once invoked, about $0.0002 per session on Opus 5.5. 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 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.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.