Claude-Pipeline: Command for Claude Code

.claude/commands/plan-review.md

plan-review is a command for Claude Code from TheAstrelo/Claude-Pipeline. It costs 0 tokens per session (373 once invoked), scanned A, original, MIT.

A command that creates an implementation plan for a task and sends it through a separate review step.

In plain words
What is it for?
Use it to plan work, review the plan, revise it when needed, and present the resulting recommendation.
Why use it?
It helps catch missing steps, impractical ideas, or conflicts with project conventions before coding begins.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is TheAstrelo/Claude-Pipeline's own configuration. It tells Claude Code how to work on Claude-Pipeline itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Claude-Pipeline configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/TheAstrelo/Claude-Pipeline/main/.claude/commands/plan-review.md
Clone the repo
git clone --depth 1 https://github.com/TheAstrelo/Claude-Pipeline

Made for: Claude Code.

Wrote 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.

agentmods badge for plan-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/theastrelo/claude-pipeline/plan-review/github.svg)](https://agentmods.dev/commands/theastrelo/claude-pipeline/plan-review)
Your own site
<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.

agentmods 80×15 button for plan-review

Your own site · 80×15
<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>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 373 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash a7cccaeb3240, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

.claude/commands/plan-review.md · 50 lines

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"]
Changes

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.

  1. 10d ago First seen · 50 lines · 0 tokens per session scan A a7cccaeb3240

Subscribe to this mod's changes

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.