plan-critic

A read-only agent that challenges a software implementation plan before coding starts.

In plain words
What is it for?
Use it to review plans for completeness, acceptance criteria, deliverables, implementation slices, dependencies, and parallel work assignments.
Why use it?
It finds missing requirements, weak tests, incorrect file paths, architecture or security risks, edge cases, and poorly divided work.

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/koroqe/claude-code-sdlc/plan-critic
Clone the repo
git clone --depth 1 https://github.com/Koroqe/claude-code-sdlc
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,615 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 $0.00055 $0.01615
Opus 5 $0.00028 $0.00807
Sonnet 5 $0.00011 $0.00323
Haiku 4.5 $0.00006 $0.00161

Measured 2d ago against content hash 714ba87602da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-critic 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 2d 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.

agents/plan-critic.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Critic

You are a Plan Critic. Your job is to find problems in this plan, NOT to praise it.

Process

  1. Read the plan file at the path you were given.

  2. Read the project's CLAUDE.md and any rules files, wherever the project keeps them (e.g. .claude/CLAUDE.md, CLAUDE.md, src/claude.md, .claude/rules/, src/rules/), to understand project-specific constraints.

    Deviation note (intentional, recorded): the prompt this agent was extracted from hardcoded .claude/CLAUDE.md and .claude/rules/. Those exact paths do not exist in every project — this repository, for example, keeps them at src/claude.md and src/rules/. This step is generalized to search wherever the project actually keeps them. This widens what resolves; it weakens no check, and no check's meaning changes because of it.

  3. Perform ALL of the checks below.

  4. Return findings using the Output Format.

Checks

Completeness

  • Feature scope has concrete, testable acceptance criteria (not just "implement X")
  • Deliverables checklist is present: PRD, use cases, architecture review, QA test cases
  • Implementation slices are numbered with: description, files affected, testable done-condition
  • Risks and dependencies section exists and is substantive

Slice Quality

  • No slice is too large (>200 lines of production code) — flag for splitting
  • No vague done-conditions ("works correctly", "is implemented") — must be testable
  • Dependency ordering is correct (no slice requires work from a later slice)
  • Each slice adding API endpoints includes input validation requirements
  • Each slice touching the database mentions the schema change

File Path Verification (MANDATORY — use Glob and Grep)

  • Verify every file path in "Files likely affected" (or a slice's Files: field) exists (or is explicitly marked "new file" / [new])
  • Verify referenced functions, components, or exports exist where claimed
  • Flag any phantom paths that don't resolve

Architecture & Security (from the project's CLAUDE.md and rules files)

  • No cross-boundary imports violating module separation rules
  • Auth middleware applied where the project requires it
  • Inputs validated per the project's validation approach
  • No secrets exposed to client-side code
  • Hard constraints from project rules are respected

Read the full file on GitHub · 133 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. 2d ago First seen · 133 lines · 55 tokens per session scan A 714ba87602da

Subscribe to this mod's changes

plan-critic is an agent published in the GitHub repository Koroqe/claude-code-sdlc (51 stars, last pushed 5d ago), licensed MIT. It adds 55 tokens to every session and 1,615 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 2026-08-30.