plan-review-gate

plan-review-gate is a skill for Claude Code from a5c-ai/babysitter. It costs 32 tokens per session (311 once invoked), scanned A, original, MIT.

A review checkpoint that sends an implementation plan to three independent reviewers for feasibility, completeness, and scope alignment.

In plain words
What is it for?
Use it to check feature plans, work-unit breakdowns, edge cases, and their fit with the original issue.
Why use it?
It catches unrealistic steps, missing work, and scope drift before the plan is shown for approval.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Good fit Use it to check feature plans, work-unit breakdowns, edge cases, and their fit with the original issue.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/a5c-ai/babysitter/plan-review-gate
About the project

Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.

a5c-ai/babysitter · 1,788 stars · on GitHub · a5c.ai

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.

Any agent
npx skills add a5c-ai/babysitter --skill plan-review-gate
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter

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-gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/a5c-ai/babysitter/plan-review-gate/github.svg)](https://agentmods.dev/skills/a5c-ai/babysitter/plan-review-gate)
Your own site
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/plan-review-gate"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/plan-review-gate/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-gate

Your own site · 80×15
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/plan-review-gate"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/plan-review-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 311 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00032 $0.00311
Opus 5 $0.00016 $0.00156
Sonnet 5 $0.00006 $0.00062
Haiku 4.5 $0.00003 $0.00031

Measured 9d ago against content hash d477f3d5e6ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

plan-review-gate 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 9d 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.

library/methodologies/metaswarm/skills/plan-review-gate/SKILL.md · 34 lines

What it actually says

  • Before presenting a plan for user approval
  • When validating work unit decomposition quality

Process

  1. Feasibility Reviewer - Can this plan actually be implemented? Technical viability, resource requirements, timeline reality
  2. Completeness Reviewer - Does the plan cover everything? Missing edge cases, untested paths, incomplete DoD items
  3. Scope & Alignment Reviewer - Does the plan match the issue? Scope creep detection, requirement traceability

All 3 must PASS before the plan is presented.

Key Rules

  • Reviewers operate independently (no shared context)
  • Each provides a binary PASS/FAIL verdict
  • Findings include specific references to plan sections
  • Failed plans require revision before re-review

Tool Use

Invoke as part of: methodologies/metaswarm/metaswarm-orchestrator (Phase 1b)

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 34 lines · 32 tokens per session scan A d477f3d5e6ce

Subscribe to this mod's changes

plan-review-gate is a skill published in the GitHub repository a5c-ai/babysitter (1,788 stars, last pushed 7d ago), licensed MIT. It adds 32 tokens to every session and 311 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 2026-09-03.