idea-critic

idea-critic is an agent for coding agents from andrewcigan/vibe-dev-plugin. It costs 55 tokens per session (1,010 once invoked), scanned A, original, MIT.

An autonomous reviewer that reduces a long list of product ideas to the strongest three to five. It checks each idea against business rules, forbidden patterns, target markets, budget limits, and scored criteria.

In plain words
What is it for?
Use it to filter ideas from planning documents, detect duplicates and rule violations, score the remaining options, and explain the final shortlist.
Why use it?
It removes the need to review every idea manually or ask for a decision at each step. It also records a specific reason when an idea is rejected.

Agent

Part of the vibe-dev plugin — 29 skills, 24 agents, 7 hooks shipped together

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/andrewcigan/vibe-dev-plugin/idea-critic
Clone the repo
git clone --depth 1 https://github.com/andrewcigan/vibe-dev-plugin

Or install vibe-dev, the plugin that ships this one along with the rest of its 29 skills, 24 agents, 7 hooks.

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 idea-critic

README.md
[![agentmods](https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/idea-critic.svg)](https://agentmods.dev/agents/andrewcigan/vibe-dev-plugin/idea-critic)
Your own site
<a href="https://agentmods.dev/agents/andrewcigan/vibe-dev-plugin/idea-critic"><img src="https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/idea-critic.svg" alt="Measured on agentmods" height="20"></a>
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 1,010 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 $0.01010
Opus 5 $0.00028 $0.00505
Sonnet 5 $0.00011 $0.00202
Haiku 4.5 $0.00006 $0.00101

Measured 4d ago against content hash 51c464ca2849, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

idea-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 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.

agents/idea-critic.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Idea Critic Agent

Роль

Второй шаг макро-методологии (FULL pipeline). Автономный — не задаёт вопросов пользователю на каждом шаге.

Принципы

  • Автономный отсев — не спрашиваешь пользователя на каждой идее
  • Жёсткие критерии — не «может быть это сработает», а «по критериям X эта идея проходит / не проходит»
  • Обоснование отсева — для каждой rejected идеи: конкретная причина
  • Top-3-5 на выход — больше = пользователь утонет в выборе

Input

  • docs/ideas-round-1.md + docs/ideas-round-2.md
  • domain-rules.yaml (для проверки на invariants и anti_patterns)
  • docs/PRODUCT.md (главная функция)

Критерии отсева

Hard filters (мгновенный reject)

  1. Противоречит invariants из domain-rules.yaml
  2. Содержит anti-pattern из domain-rules.yaml
  3. Дублирует уже принятую идею
  4. Вне target_markets (например, мобильное приложение если пользователь не делает мобильное)
  5. Бюджет > 5× от monthly_total_budget_usd — нереалистично

Score критерии (для оставшихся)

Каждая идея оценивается по 5 критериям (1-5):

  1. Бизнес-ценность — насколько решает реальную боль пользователя
  2. Уникальность — насколько отличается от существующих решений
  3. Реалистичность — можем ли мы это сделать с нашим бюджетом/стеком
  4. Скорость до результата — как быстро дойдём до validation ≥90%
  5. Расширяемость — можно ли потом нарастить функционал

Total score = сумма (max 25).

Output docs/critique-log.md

# Critique Log

## Hard-filtered (rejected immediately)

### ID-X: <название>
- **Reject reason**: противоречит invariants[i] «...»

### ID-Y: <название>
- **Reject reason**: anti-pattern AP-XX «...»

## Top-5 (passed to validation)

### ID-A: <название> | Score: 23/25
- Бизнес-ценность: 5 — главную боль решает напрямую
- Уникальность: 4 — есть аналог X но мы делаем лучше из-за Y
- Реалистичность: 5 — стек поддерживает
- Скорость: 5 — MVP компактный (5-7 фичей S/M)
- Расширяемость: 4 — после MVP легко добавить Z

### ID-B...: ...

## Borderline (Score 15-20)

### ID-N: <название> | Score: 18/25
- Рекомендация: рассмотреть позже после Top-3

Read the full file on GitHub · 113 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. 4d ago First seen · 113 lines · 55 tokens per session scan A 51c464ca2849

Subscribe to this mod's changes

idea-critic is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,010 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 2026-08-31.

Related

Other agents, from other repositories

codex-worker

CLI-backed mechanical implementer — the codex variant of fast-worker. Use for boilerplate implementation, test scaffolds, rename sweeps, or applying an already-approved plan/fix-spec when the shared selector chooses the Codex CLI backend (default gpt-5.6-luna @ xhigh) instead of the in-process sonnet worker.…

hmj1026/dhpk · 174 tokens

security-reviewer

Reviews a Wave's diff for OWASP Top 10 vulnerabilities introduced in this change. Triggered automatically by /mumei:compose after a Wave is implemented. Demands HIGH confidence for non-critical findings — false positives erode trust. Does NOT cover code quality, spec, or correctness.

iroha924/mumei · 63 tokens

spec-compliance-reviewer

Reviews a Wave's implementation against requirements.md and tasks.md to detect AC drift, scope creep, missing acceptance criteria, over-engineering, and silent re-interpretation. Triggered automatically by /mumei:compose after a Wave is implemented and before the review phase completes. Does NOT review code quality…

iroha924/mumei · 78 tokens

agy-worker

CLI-backed mechanical implementer — the agy variant of fast-worker. Use for boilerplate implementation, test scaffolds, rename sweeps, or applying an already-approved plan/fix-spec when the session wants the work offloaded to the agy (Antigravity) CLI backend (default model Gemini 3.6 Flash (High)) as a cheap…

hmj1026/dhpk · 203 tokens

code-reviewer

Expert code review specialist. MANDATORY final step before replying after any source-code Edit/Write, or after modifying .claude/ markdown (rules/agents/skills/commands/hooks/scripts) or any CLAUDE.md file. Reviews quality, security, and maintainability. Do NOT skip when: user approved a plan, change seems small…

hmj1026/dhpk · 103 tokens

spec-miner

Behavioral-spec extraction specialist. Mines flat Requirement / Invariant blocks (with id / entities / enforced / test metadata) from a brownfield codebase into openspec/specs/ /spec.md. Self-bootstrapping — no codebase-onboarding dependency. Use when onboarding an existing project to spec-driven development ("mine…

hmj1026/dhpk · 105 tokens