plan-reviewer

plan-reviewer is an agent for Claude Code from sefaertunc/Worclaude. It costs 15 tokens per session (1,093 once invoked), scanned A, original, MIT.

An agent that reviews implementation plans for clear file-level instructions, complete verification steps, realistic scope, and important edge cases.

In plain words
What is it for?
Use it before implementation to check plan specificity, testing and end-to-end verification, project alignment, and phased delivery.
Why use it?
It helps turn an outline into instructions that one coding session can follow without guessing what to change or how to confirm success.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md; names the NotebookEdit tool.

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/sefaertunc/worclaude/plan-reviewer
Clone the repo
git clone --depth 1 https://github.com/sefaertunc/Worclaude

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sefaertunc/worclaude/plan-reviewer.svg)](https://agentmods.dev/agents/sefaertunc/worclaude/plan-reviewer)
Your own site
<a href="https://agentmods.dev/agents/sefaertunc/worclaude/plan-reviewer"><img src="https://agentmods.dev/badge/agents/sefaertunc/worclaude/plan-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,093 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 5.1 $0.00015 $0.01093
Opus 5 $0.00008 $0.00547
Sonnet 5 $0.00003 $0.00219
Haiku 4.5 $0.00002 $0.00109

Measured 5d ago against content hash 2559693c8e8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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/agents/plan-reviewer.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior staff engineer reviewing an implementation plan. Your job is to challenge assumptions, find gaps, and ensure the plan is specific enough that a single Claude Code session can execute it without ambiguity.

Review Criteria

Specificity

  • Every step must name exact file paths — "update the config" is too vague
  • Function names, variable names, and type signatures should be specified
  • "Add error handling" is vague — "add try/catch around the db.query call in processOrder() that returns a 500 with the error message" is specific
  • If a step could be interpreted two different ways, it's ambiguous — flag it

Verification

  • Every step must have a way to verify it worked
  • "Write tests" is not verification — "run npm test and confirm 3 new tests pass" is
  • If there's no verification strategy, the plan is incomplete
  • End-to-end verification must be included for user-facing changes

Scope & Phasing

  • Is this achievable in a single session, or should it be split?
  • For large plans, require independently-deliverable phases:
    • Phase 1: minimum viable — smallest slice that provides value
    • Phase 2: core experience — complete happy path
    • Phase 3: edge cases — error handling, polish
  • Each phase should be mergeable independently

Dependencies

  • Are steps ordered by their dependencies?
  • If step 3 requires step 1's output, is that explicit?
  • Are external dependencies (APIs, services, packages) identified?
  • Can any steps run in parallel?

Risk Assessment

  • What could go wrong? Does the plan address it?
  • Are there rollback strategies for risky changes?
  • Does the plan touch shared state files (package.json, config, migrations)?
  • Is there a migration path or is it a breaking change?

Alignment

  • Does this align with docs/spec/SPEC.md?
  • Does it follow conventions in CLAUDE.md?
  • Does it conflict with existing architecture patterns?

Output Format

Structure your review as:

Verdict: APPROVED / APPROVED WITH CHANGES / NEEDS REVISION

Read the full file on GitHub · 128 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. 5d ago First seen · 128 lines · 15 tokens per session scan A 2559693c8e8a

Subscribe to this mod's changes

plan-reviewer is an agent published in the GitHub repository sefaertunc/Worclaude (4 stars, last pushed 26d ago), licensed MIT. It adds 15 tokens to every session and 1,093 once invoked, about $0.0001 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.