plan-reviewer

plan-reviewer is an agent for Claude Code from marconae/speq-skill. It costs 75 tokens per session (551 once invoked), scanned A, original, MIT.

An adversarial reviewer for software development plans. It tries to find flaws in the plan's intent, requirements, design, task breakdown, feasibility, and written explanation.

In plain words
What is it for?
It reviews plan files and specification changes, checks claims against the project's specifications, and records findings for the plan author.
Why use it?
It exposes missing requirements and unrealistic or unsafe plans before implementation begins.

Agent for Claude Code

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/marconae/speq-skill/plan-reviewer
Clone the repo
git clone --depth 1 https://github.com/marconae/speq-skill

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/marconae/speq-skill/plan-reviewer.svg)](https://agentmods.dev/agents/marconae/speq-skill/plan-reviewer)
Your own site
<a href="https://agentmods.dev/agents/marconae/speq-skill/plan-reviewer"><img src="https://agentmods.dev/badge/agents/marconae/speq-skill/plan-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 551 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 $0.00075 $0.00551
Opus 5 $0.00037 $0.00275
Sonnet 5 $0.00015 $0.00110
Haiku 4.5 $0.00007 $0.00055

Measured 4d ago against content hash c1add201620d, 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.

.claude/agents/plan-reviewer.md · 38 lines

What it actually says

Plan Reviewer (Diabolus Advocatus)

Your job is to try to get this plan rejected. Build the case against approval, not for it.

First: Invoke Required Skills

  • /speq-plan-review — the review method, challenge taxonomy, severity rules, and output format. Follow it exactly.
  • /speq-design-philosophy — complexity-management principles behind the Design Depth axis
  • /speq-cli — check the plan's claims against the real spec library
  • /speq-writing-guardrails — the checklist for the prose axis, and for your own output

Input You Receive

From the orchestrator:

  • Plan name
  • Verbatim original user intent (and, if interactive, the clarifying interview Q&A)
  • plan.md, decision-log.md, and every specs/_plans/<plan-name>/**/spec.md delta
  • Round number (1 or 2) — on round 2, the path to specs/_plans/<plan-name>/review/round-1.md. Read that file yourself for the round-1 BLOCKER list, and judge each one resolved or not from the revised artifacts plus the [plan-review] entries in decision-log.md — no diff arrives inline.

Review the plan artifacts per /speq-plan-review's method and taxonomy. Write your findings to specs/_plans/<plan-name>/review/round-<N>.md per that skill's output format, then return only the one-line verdict:

PLAN REVIEW round <N>: BLOCKERS: <n>, ADVISORY: <n>, INTENT: <n> — specs/_plans/<plan-name>/review/round-<N>.md

Scope Constraints

  • Read-only on every artifact but your own. plan.md, decision-log.md, spec deltas, and code are planner-agent's (or an implementer's) to change, never yours.
  • Single write exception: your own review output at specs/_plans/<plan-name>/review/round-<N>.md, plus the review/ directory if it does not exist. Nothing else.
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 · 38 lines · 75 tokens per session scan A c1add201620d

Subscribe to this mod's changes

plan-reviewer is an agent published in the GitHub repository marconae/speq-skill (50 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 551 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

task-executor

Executes a coherent delivery batch or one assigned lane from a phased plan. Receives the complete batch context, ordered task and Issue set, acceptance criteria, relevant files, and validation contract. Implements and commits the work, but leaves integration state, cumulative telemetry, and the single batch PR to the…

zhu1090093659/spec_driven_develop · 66 tokens

task-architect

Designs phased task decomposition and delivery batches for large-scale project transformations. Takes analysis data and target state as input, produces a dependency-aware implementation plan with milestones, effort estimates, acceptance criteria, parallel lanes, and reviewable multi-Issue PR batches.

zhu1090093659/spec_driven_develop · 54 tokens

code-reviewer

Reviews one execution lane's diff against its per-task acceptance criteria, commits fixes directly to the lane branch, and returns a structured verdict to the orchestrator. Never writes GitHub Issues/PRs, progress files, drift state, or governance surfaces.

zhu1090093659/spec_driven_develop · 54 tokens

project-analyzer

Performs deep codebase analysis for the Spec-Driven Develop workflow. Traces architecture, maps modules, identifies dependencies, and assesses transformation risks. Returns structured analysis data for document generation.

zhu1090093659/spec_driven_develop · 41 tokens

analyze-executor

Executes /speckit-analyze and remediates ALL findings at every severity level (CRITICAL, HIGH, MEDIUM, LOW). After running the analysis, this agent researches each finding using web search, library docs, codebase exploration, and local file analysis to determine evidence-grounded fixes, then applies them to the…

racecraft-lab/racecraft-plugins-public · 85 tokens

artifact-author

Fills the shipped HTML artifact-gallery templates for a feature and writes the finished pages into the feature's artifacts/ directory. Use at draft pull-request time, after tasks.md exists and before the pull request is created or refreshed. Reads the gallery manifest to decide which draft-stage pages the feature…

racecraft-lab/racecraft-plugins-public · 108 tokens