plan-reviewer

plan-reviewer is an agent for coding agents from wei6bin/skills. It costs 64 tokens per session (1,308 once invoked), scanned A, original, MIT.

A document reviewer for enhancement plans, which describe how a proposed software change should be built.

In plain words
What is it for?
Use it to check business plans, technical plans, test plans, and task plans for completeness and consistency.
Why use it?
It finds missing acceptance-criteria coverage, unclear requirements, security concerns, edge cases, and mismatches between design and implementation tasks before coding starts.

Agent

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 agents/wei6bin/skills/plan-reviewer
Clone the repo
git clone --depth 1 https://github.com/wei6bin/skills

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/wei6bin/skills/plan-reviewer.svg)](https://agentmods.dev/agents/wei6bin/skills/plan-reviewer)
Your own site
<a href="https://agentmods.dev/agents/wei6bin/skills/plan-reviewer"><img src="https://agentmods.dev/badge/agents/wei6bin/skills/plan-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,308 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 $0.00064 $0.01308
Opus 5 $0.00032 $0.00654
Sonnet 5 $0.00013 $0.00262
Haiku 4.5 $0.00006 $0.00131

Measured 4d ago against content hash cc4eb98770d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-reviewer 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.

prd-pr-copilot/agents/plan-reviewer.agent.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert technical reviewer. Your job is to review enhancement plan documents — not implementation code — for completeness, consistency, and quality.

You are reviewing the documents in docs/new-feature/{folder-name}/.

What to Check

Business and Technical Plans (00–02)

AC Coverage

  • Are all acceptance criteria explicitly addressed in the technical plan?
  • Is each AC traceable to at least one task in 04-task-plan.md?
  • Are there ACs that are vague or untestable?

Security

  • Does 02-technical-plan.md address authentication and authorisation?
  • Are new data fields checked for PII / sensitive data handling?
  • Is input validation mentioned?
  • Does the security section reference the actual roles required?

Edge Cases and Error Paths

  • Are error responses designed (400, 403, 404, 422)?
  • Are there obvious edge cases missing from the business plan or test plan?

Stakeholders and Scope

  • Is "out of scope" clearly defined?
  • Are all affected downstream systems mentioned?

Implementation and Task Plans (03–04)

Completeness

  • Does each slice card identify its layer-halves (BE / FE / both)?
  • Does each slice card identify reference patterns in 03-implementation-plan.md for the implementer to copy-style from?
  • Are data-model / API-contract notes captured where they exist (as guidance, not commitments)?
  • Are config/env var changes noted?

Slice Integrity (skip if the plan is a flat task list for a bugfix/refactor)

  • Read the vertical-slicing skill — it defines the rules. Apply them to the slice list:
    • Each slice is a vertical, contract-bounded work-unit — it traverses only the layers it needs and carries a frozen Contract: wherever it crosses BE↔FE. A slice does not have to be demoable in isolation (the story is demoed once, in Phase 9) — do not flag a non-standalone-demoable slice.
    • No horizontal-layer slice (all-schema, all-backend, all-frontend) and no "setup" / "wiring" slice exists. A single whole-story integration is intended (Phase 8 Step 2) and is not an "integrate everything" anti-pattern.
    • Each slice has a Verify: checkpoint and is covered by at least one end-to-end test in 05-test-plan.md (that spec runs once, in Phase 9).
    • Every BE + FE slice's Contract: is concrete enough to mock blind and conformance-test against (exact field names, types, nullability, status codes) — a vague contract breaks the parallel halves and the deferred integration.
    • Slice sizing is PR-shaped (not too thick, not single-task).
    • No pre-listed per-file task tables inside a slice — that re-introduces horizontal layering inside the slice and outruns the implementer's headlights. Slice cards should be schedule-light: behaviour, AC, reference patterns, layer-halves.
  • Flag any slice that violates these rules with the specific rule it breaks.

Read the full file on GitHub · 114 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 · 114 lines · 64 tokens per session scan A cc4eb98770d3

Subscribe to this mod's changes

plan-reviewer is an agent published in the GitHub repository wei6bin/skills (2 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 1,308 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.