Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add juanmhidalgo/claude-plugins/plugin install code-reviewWrote 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/pipeline)<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/pipeline"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/pipeline.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 | $0.00033 | $0.01154 |
| Opus 5 | $0.00016 | $0.00577 |
| Sonnet 5 | $0.00007 | $0.00231 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
pipeline 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 6d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Repository: !
git remote get-url origin - Current branch: !
git branch --show-current - PR Number: $ARGUMENTS
- Date: !
date +%Y-%m-%d - Working tree clean: !
git status --short
Phase 0: Validate
- PR number was provided (from
$ARGUMENTS) - Working tree is clean. If dirty, STOP and ask user to commit or stash.
- PR is open:
gh pr view $ARGUMENTS --json state -q '.state'must beOPEN. If draft/closed/merged, STOP.
Autonomous mode
This pipeline runs without asking for input. For the full decision-rules table covering simple fixes, ambiguous cases, test failures, coverage misses, and scope leaks from auto-formatters, see @pipeline.references/phase-details.md (Autonomous mode rules section).
NEVER ask for input. Only stop if tests fail after 2 retry attempts or if validation fails.
Phase 1: Triage
Fetch all PR comments and verify each in parallel using the comment-verifier agent. Collect VALID BUG / FALSE POSITIVE verdicts with ref_id preserved.
For the exact script invocation and verifier-prompt format, see @pipeline.references/phase-details.md (Phase 1 detail).
Phase 2: Dismiss false positives
For each FALSE POSITIVE, run pr-resolve-comment.sh ... dismiss "REASON". For canonical reason phrases, see @pipeline.references/phase-details.md (Phase 2 detail).
Phase 3: Plan fixes
For each VALID BUG:
- Read affected code
- Determine the minimal fix
- Note which files are affected
Group fixes by file. Fixes touching different files can run in parallel; fixes touching the same file run sequentially.
Phase 4: Implement fixes
- Parallel (different files) — spawn
fix-implementeragents in parallel. - Sequential (same file) — run
fix-implementerone at a time to avoid conflicts. - After all fixes — read each modified file to verify no syntax errors.
- Scope check — discard auto-formatter-induced changes to files NOT in the fix plan via
git checkout -- <file>; log the count.
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.
- 6d ago First seen · 120 lines · 33 tokens per session scan A 893abe9e32c4
pipeline is a command published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 12d ago), licensed MIT. It adds 33 tokens to every session and 1,154 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
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
code-review
Code review for branch changes. Analyzes git diff between branches with multi-level depth (low/medium/high). Matches changes against task description. Returns structured report with severity levels and verdict.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
advanced-code-review-context
Advanced Code Review Phase 2: Context Analysis - load previous reviews, PR history, declined items.