Borrowing it
Nothing to install: this file belongs to TheAstrelo/Claude-Pipeline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TheAstrelo/Claude-Pipeline/main/.claude/commands/plan-review.mdgit clone --depth 1 https://github.com/TheAstrelo/Claude-PipelineWrote 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/theastrelo/claude-pipeline/plan-review)<a href="https://agentmods.dev/commands/theastrelo/claude-pipeline/plan-review"><img src="https://agentmods.dev/badge/commands/theastrelo/claude-pipeline/plan-review/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/theastrelo/claude-pipeline/plan-review"><img src="https://agentmods.dev/badge/commands/theastrelo/claude-pipeline/plan-review.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 | $0.00000 | $0.00373 |
| Opus 5 | $0.00000 | $0.00187 |
| Sonnet 5 | $0.00000 | $0.00075 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
plan-review 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.
What it actually says
Create an implementation plan and automatically review it for the following task:
$ARGUMENTS
Execute these steps IN SEQUENCE. Do NOT skip steps.
Step 1: Plan
Use the planner agent (Task tool with subagent_type="planner"). Pass it the original task description.
Prompt: "Create a detailed implementation plan for: [TASK]. Explore the codebase to understand existing patterns before planning."
After the planner finishes, provide a brief summary of the plan to the user.
Step 2: Review Plan
Use the plan-reviewer agent (Task tool with subagent_type="plan-reviewer"). Pass it the full plan from Step 1.
Prompt: "Review this implementation plan for completeness, feasibility, and convention compliance: [PLAN]"
- If verdict is APPROVED: present the plan to the user with a green light.
- If verdict is APPROVED WITH CHANGES: present the plan with the suggested changes highlighted.
- If verdict is NEEDS REVISION: go back to Step 1 with the reviewer's feedback. Maximum 2 revision cycles — if still not approved after 2 cycles, present the best version and note the concerns.
Final Summary
After all steps complete, provide a summary:
## Plan Review Complete
### Task
[Original task description]
### Plan Summary
[What was planned — files to change, approach, key decisions]
### Review Verdict: [APPROVED | APPROVED WITH CHANGES | NEEDS REVISION]
[Key findings and any suggested changes]
### Next Steps
[What the user should do — e.g., "Run `/auto-pipeline` (or `bash run-pipeline.sh \"<task>\"`) to implement" or "Approve and I'll start coding"]
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 · 50 lines · 0 tokens per session scan A a7cccaeb3240
plan-review is a command published in the GitHub repository TheAstrelo/Claude-Pipeline (45 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 373 tokens. 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 2026-08-30.
Other commands, from other repositories
status
Summarise what Fabrik is doing right now — board state, in-flight workers, worktrees with uncommitted changes.
setup-forge
First-run onboarding — asks name/goal/project-type/language, then beginner-safe API-key setup, then scaffolds the per-project Forge system. User-invoked only. Run once per project. Subcommands: doctor · keys · reset.
spreadsheet-audit
Perform a 6-step audit of an Excel spreadsheet for formula correctness, formatting consistency, data integrity, boss-auditable simplicity, and spec compliance. Uses the excel-screenshot MCP server tools — no Excel installation required.
custom-brief
Deep-research a specific topic and produce a comprehensive news-focused briefing with optional Notion/Obsidian/Teams/Slack publishing.
diagnose-roast-curve
Diagnose a logged roast curve for the classic defects — crash, flick, stall/bake, tipping, scorching — and assess RoR smoothness and development-time ratio.
gsd:resume-work
Resume work from previous session with full context restoration.