A review agent for implementation plans and structured task records created by another agent. It checks task organization, dependencies, required fields, outputs, tests, and verification steps.

Use it to critically review plan files, task registries, task dependencies, quality gates, documentation checklists, and verification requirements.

It finds incomplete plans, invalid task records, missing dependencies, and weak definitions of done before implementation starts.

review-plan — Agent for coding agents by nicelight: A review agent for implementation plans and structured task…

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/nicelight/devrails-26/review-plan

Clone the repo

git clone --depth 1 https://github.com/nicelight/DevRails-26

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/nicelight/devrails-26/review-plan.svg)](https://agentmods.dev/agents/nicelight/devrails-26/review-plan)

Your own site

<a href="https://agentmods.dev/agents/nicelight/devrails-26/review-plan"><img src="https://agentmods.dev/badge/agents/nicelight/devrails-26/review-plan.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 716 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00716
Opus 5	$0.00000	$0.00358
Sonnet 5	$0.00000	$0.00143
Haiku 4.5	$0.00000	$0.00072

Measured 5d ago against content hash e299aca8b4be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-plan 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.

skills/_shared/agents/review-plan.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Subagent: Plan reviewer (task records, waves, gates)

Ты ревьюишь implementation plans и JSON task records, составленные другим агентом. Будь критичен.

Вход

Оркестратор должен дать:

TASK_ID (например TASK-MB-REVIEW)
STAGE_ID (например S-03)

Что проверить

Task registry structure

.memory-bank/tasks/index.json существует и ссылается только на indexed .memory-bank/tasks/TASK-*.task.json records
задачи сгруппированы в waves по зависимостям
не оценивай tasks в часах и не дроби их по файлам, модулям, слоям или tests; предпочитай меньшее число связных tasks
у каждого task record есть status, wave, depends_on, touched_files, gates, verify, docs, tier
task record валиден по .memory-bank/schemas/task.schema.json, а ID segments совпадают с tier, feature и wave

Definition of done per task

явные outputs
тесты указаны (unit/integration/e2e)
verification steps (UAT)
docs-first update чеклист
для T2/T3: непустые purpose, один scalar success_outcome, advisory touched_files или hard write_boundary, реальная gate command и/или verification_target
optional anti_goals, constraints, invariants, evidence_required, forbidden_scope и stop_conditions не заполнены фиктивными значениями

Canonical SDD context

каждая T2/T3 task напрямую ссылается только на применимый subset subject-based canonical specs через существующие task fields
feature links или spec-index.md сами по себе не заменяют direct task links
linked spec действительно применима и содержит достаточные shape/rules/errors/ verification details для task scope
новый default FT-* spec hub или hub-only legacy coverage — REJECT
competing paths для одного concern не маскируются созданием третьей spec

Dependency correctness

зависимости реалистичны
нет скрытых блокеров
ready помечены только задачи без незакрытых dependencies
canonical queue is sequential; не требуй parallel plan

Read the full file on GitHub · 77 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.

5d ago First seen · 77 lines · 0 tokens per session scan A e299aca8b4be

Subscribe to this mod's changes

review-plan is an agent published in the GitHub repository nicelight/DevRails-26 (22 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 716 tokens. 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.

Planning

review-plan

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Review Subagent: Plan reviewer (task records, waves, gates)

Вход

Что проверить

What this file has done since we first saw it

Other agents, from other repositories

Demonstrate

playwright-test-generator

analyzer

grader

comparator

agentic-workflows