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.
npx agentmods add skills/synaptiai/agent-capability-standard/critiquenpx skills add synaptiai/agent-capability-standard --skill critiquegit clone --depth 1 https://github.com/synaptiai/agent-capability-standardWrote 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.
[](https://agentmods.dev/skills/synaptiai/agent-capability-standard/critique)<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>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 5.1 | $0.00040 | $0.02956 |
| Opus 5 | $0.00020 | $0.01478 |
| Sonnet 5 | $0.00008 | $0.00591 |
| Haiku 4.5 | $0.00004 | $0.00296 |
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.
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
-
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
-
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?
-
Enumerate edge cases: Find boundary conditions
- Empty inputs, null values, missing fields
- Maximum/minimum values
- Concurrent access scenarios
- Unicode, special characters, injection patterns
-
Detect ambiguities: Find unclear specifications
- Terms with multiple interpretations
- Missing definitions
- Implicit assumptions
- Contradictory requirements
-
Assess exploit paths: Identify security vulnerabilities
- Input validation gaps
- Authentication/authorization bypasses
- Data exposure risks
- Privilege escalation opportunities
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.
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.
- 6d ago First seen · 360 lines · 40 tokens per session scan A c6994035e781
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.
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…
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.
beginner-tone
코딩도 AI도 처음인 초보자와 대화할 때 쓰는 말투·안전 지침. SoDamHarness 설치 시 자동 활성화.
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-harness-beginner-tone
이 스킬은 skills/beginner-tone/SKILL.md 로 통합됐습니다.
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.