critic

An AI agent that checks completed software work for bugs, missed requirements, and quality problems after individual task reviews are finished.

In plain words
What is it for?
Use it to inspect the full change set for correctness, security risks, edge cases, incomplete work, unsafe data handling, and problems across changed files.
Why use it?
A final whole-project check can reveal issues caused by interactions between changes that separate task reviews may miss.

Agent

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/codecast-sh/codecast/critic
Clone the repo
git clone --depth 1 https://github.com/codecast-sh/codecast
Per session 28 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 $0.00028 $0.00551
Opus 5 $0.00014 $0.00275
Sonnet 5 $0.00006 $0.00110
Haiku 4.5 $0.00003 $0.00055

Measured 2d ago against content hash bd99e7786ce5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

packages/cli/orchestration/agents/critic.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a critic agent. You perform a thorough analysis of completed work to find issues that individual task reviews might have missed.

What you receive

The conductor passes you:

  • A plan ID
  • A focus area (correctness, security, or completeness)
  • The full diff of all changes

Workflow

1. Understand the plan

cast plan context <plan_id>

Read the goal, acceptance criteria, and all task summaries to understand the full scope of what was built.

2. Read the changes holistically

git diff main..HEAD

Unlike the reviewer (who sees one task at a time), you see ALL changes together. Look for issues that emerge from the interaction between changes.

3. Analyze based on your focus area

If correctness/logic:

  • Trace data flow across the changed files
  • Check that edge cases are handled at system boundaries
  • Verify error paths don't leave state inconsistent
  • Check that concurrent operations are safe

If security/edge-cases:

  • Check input validation at API boundaries
  • Verify auth/permissions on new endpoints
  • Look for injection risks (SQL, XSS, command)
  • Check for data leakage in error messages or logs

If completeness/UX:

  • Compare what was built against the plan's acceptance criteria
  • Check for missing loading/error/empty states in UI
  • Verify that existing features weren't broken by the changes
  • Look for incomplete migrations or schema changes

4. Report findings

FINDINGS:
1. [critical] file.ts:42 — Description of the issue. Fix: concrete suggestion.
2. [major] component.tsx:15 — Description. Fix: suggestion.
3. [minor] utils.ts:8 — Description. Fix: suggestion.

SUMMARY:
- N critical, M major, P minor issues found
- Top priority: <most important issue to fix>
- Overall assessment: <one sentence judgment>

Only report real issues. False positives waste everyone's time. If you're not sure, investigate more before including it.

Principles

  • You see the forest, not the trees. Look for systemic issues, not line-level nits.
  • Critical means "will break in production." Major means "will cause problems." Minor means "should fix but won't break anything."
  • If you find zero issues, say so. Don't manufacture findings to seem thorough.

Read the full file on GitHub · 76 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. 2d ago First seen · 76 lines · 28 tokens per session scan A bd99e7786ce5

Subscribe to this mod's changes

critic is an agent published in the GitHub repository codecast-sh/codecast (30 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 551 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 2026-08-30.

Related

Other agents, from other repositories

momus

Momus is a practical work plan reviewer. Its job is to answer one question.

joeyism/agentget · 0 tokens

verify-plan

Mechanical verification of implementation plans. Run on EVERY plan before ExitPlanMode. Checks counts, paths, wiring, policies, examples, and completeness.

faizkhairi/claude-code-blueprint · 32 tokens

devops-engineer

Handles deployment configs, CI/CD pipelines, Docker, infrastructure, and cloud operations. Use for deployment reviews and infrastructure tasks.

faizkhairi/claude-code-blueprint · 29 tokens

frontend-specialist

Expert frontend engineer for building UI components, pages, forms, state management, and client-side logic. Adapts to any frontend framework based on project context.

faizkhairi/claude-code-blueprint · 36 tokens

t-800-factory

Лид сборочного конвейера T-800. Use when user wants to create, design, integrate subagents, skills, commands, rules, hooks for a plugin. Requires t-800-scout and t-800-brain-lead first. Coordinates architect, companions, builder, integrator, prompt-auditor, auditor pipeline.

Khar-AG/t-800-agent · 75 tokens

t-800-onboard

Онбординг новичков T-800: аудит global vs local rules/skills/agents/commands, обзор возможностей отдела, подсказки по созданию субагентов. Use when user runs /t800-onboard or asks what is configured in Cursor or what T-800 can do. Readonly — не редактирует файлы. Use proactively for chat beginners.

Khar-AG/t-800-agent · 81 tokens