agentmods.dev

plan-review-backend

plan-review-backend is a command for coding agents from bradlay/claude-code-recipes. It costs 56 tokens per session (673 once invoked), scanned A, original, MIT.

A command for choosing the AI service that reviews your coding plans when you leave plan-review mode. It offers only services that currently pass its availability check and keeps the choice for the session.

In plain words
What is it for?
Use it to select, change, or clear the plan-review service used for later plan reviews.
Why use it?
It gives you control over which AI reviews your plan and avoids selecting a service that is not working.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the plan-review-loop plugin — 1 command shipped together

not rated 2 13d ago A scan 56 tokens original MIT
View the source file bradlay/claude-code-recipes
Install

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.

agentmods
npx agentmods add commands/bradlay/claude-code-recipes/plan-review-backend
Clone the repo
git clone --depth 1 https://github.com/bradlay/claude-code-recipes

Or install plan-review-loop, the plugin that ships this one along with the rest of its 1 command.

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-backend

README.md
[![agentmods](https://agentmods.dev/badge/commands/bradlay/claude-code-recipes/plan-review-backend.svg)](https://agentmods.dev/commands/bradlay/claude-code-recipes/plan-review-backend)
Your own site
<a href="https://agentmods.dev/commands/bradlay/claude-code-recipes/plan-review-backend"><img src="https://agentmods.dev/badge/commands/bradlay/claude-code-recipes/plan-review-backend.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 673 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00056 $0.00673
Opus 5 $0.00028 $0.00336
Sonnet 5 $0.00011 $0.00135
Haiku 4.5 $0.00006 $0.00067

Measured 4d ago against content hash 9286cf53c37f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-review-backend 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 4d 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.

plugins/plan-review-loop/commands/plan-review-backend.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/plan-review-loop:plan-review-backend

Pick the plan-review backend for this session. The choice is sticky: every ExitPlanMode reviews against it until you change it or the session ends.

The user invoked this command with: $ARGUMENTS

What to do

  1. FIRST, check whether a backend is already pinned for this session:

    printenv CLAUDE_PLAN_REVIEW_CHAIN

    If that prints a non-empty value, the review backend is PINNED and there is nothing to choose. This is the case in an autosre claude (local) session, which pins local so reviews stay 100% on the local qwen. Tell the user the backend is pinned to that value and STOP — do NOT probe, do NOT show a picker. The picker is only for sessions where no chain is pinned (e.g. bare cloud claude).

  2. If $ARGUMENTS contains clear, run:

    CLAUDE_PLUGIN_DATA="${CLAUDE_PLUGIN_DATA}" "${CLAUDE_PLUGIN_ROOT}/bin/plan-review-select" --latest-session --clear

    Then tell the user the next ExitPlanMode will ask again, and stop.

  3. Otherwise, find which backends are verified working right now:

    CLAUDE_PLUGIN_DATA="${CLAUDE_PLUGIN_DATA}" "${CLAUDE_PLUGIN_ROOT}/bin/plan-review-probe" --online --json

    Only offer backend keys whose probe result is ok (one of: opus, sonnet, codex, gemini). If none pass, report that and stop.

  4. Use AskUserQuestion to ask which backend to use, one option per verified key (label them: Opus 4.8 / Sonnet 5 / codex gpt-5.6-sol / Gemini 3.1 Pro).

  5. Persist the choice (replace <key> with the chosen key):

    CLAUDE_PLUGIN_DATA="${CLAUDE_PLUGIN_DATA}" "${CLAUDE_PLUGIN_ROOT}/bin/plan-review-select" --latest-session --reprobe <key>

    --reprobe confirms the backend is reachable before saving. Report the result to the user.

Notes

  • This is the same selection the ExitPlanMode hook prompts for; running it ahead of time means the hook won't interrupt your first plan exit.
  • Under autoswe runs the backend is always the local qwen and is not asked.
  • For a permanent non-interactive default, set CLAUDE_PLAN_REVIEW_CHAIN=<key> or CLAUDE_PLAN_REVIEW_AUTOSELECT=<key> in your environment.

Read the full file on GitHub · 66 lines

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. 4d ago First seen · 66 lines · 56 tokens per session scan A 9286cf53c37f

Subscribe to this mod's changes

plan-review-backend is a command published in the GitHub repository bradlay/claude-code-recipes (2 stars, last pushed 13d ago), licensed MIT. It adds 56 tokens to every session and 673 once invoked, about $0.0003 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.

Building agentsPlanning
Related

Other commands, from other repositories

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

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.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

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.

github/spec-kit · 35 tokens

implement

Execute the implementation plan by processing and executing all tasks defined in tasks.md.

github/spec-kit · 14 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens