critique

critique is a skill for Claude Code from synaptiai/agent-capability-standard. It costs 40 tokens per session (2,956 once invoked), scanned A, original, Apache-2.0.

A review method for finding ways that a plan, code, design, or document could fail, become unclear, or be misused.

In plain words
What is it for?
Use it to stress-test logic, review security, examine failure scenarios, rate findings by severity, and suggest fixes.
Why use it?
It exposes edge cases, hidden assumptions, and possible attack paths before they become real problems.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter.

Part of the agent-capability-standard plugin — 42 skills, 2 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 skills/synaptiai/agent-capability-standard/critique
Any agent
npx skills add synaptiai/agent-capability-standard --skill critique
Clone the repo
git clone --depth 1 https://github.com/synaptiai/agent-capability-standard

Made for: Claude Code.

Or install agent-capability-standard, the plugin that ships this one along with the rest of its 42 skills, 2 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 critique

README.md
[![agentmods](https://agentmods.dev/badge/skills/synaptiai/agent-capability-standard/critique.svg)](https://agentmods.dev/skills/synaptiai/agent-capability-standard/critique)
Your own site
<a href="https://agentmods.dev/skills/synaptiai/agent-capability-standard/critique"><img src="https://agentmods.dev/badge/skills/synaptiai/agent-capability-standard/critique.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,956 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 5.1 $0.00040 $0.02956
Opus 5 $0.00020 $0.01478
Sonnet 5 $0.00008 $0.00591
Haiku 4.5 $0.00004 $0.00296

Measured 6d ago against content hash c6994035e781, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

critique 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 6d 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/critique/SKILL.md · 360 lines

How it starts

The opening of the file, as written. The whole thing — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intent

Systematically analyze a target (plan, code, design, document) to identify failure modes, edge cases, ambiguities, and potential exploits. Produce actionable findings with severity ratings and mitigation recommendations.

Success criteria:

  • All major failure modes identified
  • Edge cases documented with reproduction scenarios
  • Ambiguities flagged with clarification requests
  • Security/exploit risks rated appropriately
  • Each finding has actionable recommendation

Compatible schemas:

  • schemas/output_schema.yaml

Inputs

Parameter Required Type Description
target Yes string or object Plan, code, design, or document to critique
focus_areas No array Specific areas to examine (security, performance, logic, etc.)
severity_threshold No string Minimum severity to report: low, medium, high, critical
context No object Additional context about the target
adversarial No boolean Enable adversarial/red-team thinking (default: true)

Procedure

  1. Understand the target: Analyze what is being critiqued

    • Read and comprehend the target fully
    • Identify the purpose and intended behavior
    • Note stated assumptions and constraints
    • Understand success criteria
  2. Identify failure modes: Find ways the target could fail

    • What happens under unexpected inputs?
    • What if dependencies are unavailable?
    • What if timing assumptions are wrong?
    • What if scale exceeds expectations?
  3. Enumerate edge cases: Find boundary conditions

    • Empty inputs, null values, missing fields
    • Maximum/minimum values
    • Concurrent access scenarios
    • Unicode, special characters, injection patterns
  4. Detect ambiguities: Find unclear specifications

    • Terms with multiple interpretations
    • Missing definitions
    • Implicit assumptions
    • Contradictory requirements
  5. Assess exploit paths: Identify security vulnerabilities

    • Input validation gaps
    • Authentication/authorization bypasses
    • Data exposure risks
    • Privilege escalation opportunities

Read the full file on GitHub · 360 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 360 lines · 40 tokens per session scan A c6994035e781

Subscribe to this mod's changes

critique is a skill published in the GitHub repository synaptiai/agent-capability-standard (4 stars, last pushed 6d ago), licensed Apache-2.0. It adds 40 tokens to every session and 2,956 once invoked, about $0.0002 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 skills, from other repositories

evaluate-options

Research and evaluate implementation options before presenting a recommendation. Use when multiple approaches exist for a problem and a decision is needed. Launches one background research agent per option in parallel, collects evidence-backed findings, then presents a recommendation grounded in observed data — not…

bitflight-devops/hallucination-detector · 97 tokens

delegate

Quick delegation template for sub-agent prompts. Use when assigning work to a sub-agent, before invoking the Task tool, or when preparing prompts for specialized agents. Provides the WHERE-WHAT-WHY framework. For comprehensive delegation guidance, activate the agent-orchestration how-to-delegate skill.

bitflight-devops/hallucination-detector · 60 tokens

beginner-tone

코딩도 AI도 처음인 초보자와 대화할 때 쓰는 말투·안전 지침. SoDamHarness 설치 시 자동 활성화.

sodam-ai/SoDam-Harness-Eng · 34 tokens

sodam-harness-self-check

작업을 끝내거나 "다 됐어요"라고 말하기 전에 실제로 작동하는지 점검하고 증거를 보여줄 때 사용. 위험·중요 작업 마무리, 완료 선언, 검증 요청 시 적용.

sodam-ai/SoDam-Harness-Eng · 51 tokens

sodam-harness-beginner-tone

이 스킬은 skills/beginner-tone/SKILL.md 로 통합됐습니다.

sodam-ai/SoDam-Harness-Eng · 25 tokens

ai-safe-driver

Use when the agent keeps repeating a mistake, ignores a correction, retries a failed tool unchanged, breaks an output format again, drifts from the latest request, or makes excuses instead of diagnosing recurrence. Also use for a conversation health check, compaction decision, or new-session question.

ssauma/ai-safe-driver · 61 tokens