agentmods.dev

plan-reviewer

plan-reviewer is an agent for Claude Code from marconae/speq-skill. It costs 47 tokens per session (579 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

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

not rated 54repo +1 changed 14d ago A scan 47 tokens original MIT

Good fit It reviews plan files and specification changes, checks claims against the project's specifications, and records findings for the plan author.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/marconae/speq-skill/plan-reviewer
View source ↗ marconae/speq-skill
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.

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/github.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/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-reviewer

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 579 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.
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 $0.00047 $0.00579
Opus 5.5 $0.00019 $0.00232
Sonnet 5.5 $0.00009 $0.00116
Haiku 4.5 $0.00005 $0.00058

Measured 14d ago against content hash a99338ee87f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 14d 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 · 45 lines

What it actually says

Plan Reviewer (Diabolus Advocatus)

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-adr-rules: the rules behind [ADR_OVERPROMOTION], the ADR trigger for [ARCHITECTURE_DRIFT], and the ADR conflict check for [ADR_CONFLICT]
  • /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 the path to the clarifying interview Q&A: ## Interview in decision-log.md)
  • plan.md, decision-log.md, and every specs/_plans/<plan-name>/**/spec.md delta, and specs/_plans/<plan-name>/architecture.md when present
  • Optionally, a pointer to specs/_plans/<plan-name>/notes/planning.md (planner-agent's hand-off note). Read it for orientation: files checked, searches run. It is not authoritative and exempts no artifact from challenge.

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

PLAN REVIEW: BLOCKERS: <n>, FINDINGS: <n>, INTENT: <n> — specs/_plans/<plan-name>/review/review.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/review.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. 14d ago Changed · -2 lines · -28 tokens per session a99338ee87f1
  2. 25d ago Changed · +6 lines 2db3f06bc52a
  3. 1mo ago Changed 586b4f275797
  4. 1mo ago Changed · +1 lines b16ce7ca8439
  5. 1mo ago Changed 3bac525b5c8d
  6. 2mo ago Changed · +2 lines 5358cc99bbab
  7. 2mo 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 (54 stars, last pushed 15d ago), licensed MIT. It adds 47 tokens to every session and 579 once invoked, about $0.0002 per session on Opus 5.5. 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.

Claude CodePlanningagent-skillsagentic-aiartificial-intelligenceskillsspec-driven-development
Related

plan-reviewer compared with agents from other repositories

plan-reviewer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
plan-reviewermarconae/speq-skillAgent5415d agoMITA47Claude Code
ase-docs-shortenrse/aseAgent63todayApache-2.0A9Claude Code
task-architectzhu1090093659/spec_driven_developAgent9943mo agoMITA54Claude Code
task-executorzhu1090093659/spec_driven_developAgent9943mo agoMITA66Claude Code
analyze-executorracecraft-lab/racecraft-plugins-publicAgent59d agoMITA88Claude Code
implement-executorracecraft-lab/racecraft-plugins-publicAgent59d agoMITA86Claude Code
consensus-tiebreakerracecraft-lab/racecraft-plugins-publicAgent59d agoMITA87Claude Code