quality-critic

quality-critic is a skill for Claude Code from ensingm2/AI-threat-modeling-rulesets. It costs 45 tokens per session (1,230 once invoked), scanned A, original, MIT.

A review guide that checks security analyses for unsupported claims, missing coverage, and weak reasoning. It is designed to challenge an assessment rather than produce or repair it.

In plain words
What is it for?
Reviewing threat models, including STRIDE-based security assessments. It can identify gaps and analytical problems before a report is approved.
Why use it?
It helps catch invented technical details, overlooked system parts, and risk ratings that lack evidence. It also checks whether claims can be traced to documentation.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Reviewing threat models, including STRIDE-based security assessments. It can identify gaps and analytical problems before a report is approved.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ensingm2/ai-threat-modeling-rulesets/quality-critic
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.

Any agent
npx skills add ensingm2/AI-threat-modeling-rulesets --skill quality-critic
Clone the repo
git clone --depth 1 https://github.com/ensingm2/AI-threat-modeling-rulesets

Made for: Claude Code.

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 quality-critic

README.md
[![agentmods](https://agentmods.dev/badge/skills/ensingm2/ai-threat-modeling-rulesets/quality-critic/github.svg)](https://agentmods.dev/skills/ensingm2/ai-threat-modeling-rulesets/quality-critic)
Your own site
<a href="https://agentmods.dev/skills/ensingm2/ai-threat-modeling-rulesets/quality-critic"><img src="https://agentmods.dev/badge/skills/ensingm2/ai-threat-modeling-rulesets/quality-critic/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for quality-critic

Your own site · 80×15
<a href="https://agentmods.dev/skills/ensingm2/ai-threat-modeling-rulesets/quality-critic"><img src="https://agentmods.dev/badge/skills/ensingm2/ai-threat-modeling-rulesets/quality-critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,230 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00045 $0.01230
Opus 5 $0.00023 $0.00615
Sonnet 5 $0.00009 $0.00246
Haiku 4.5 $0.00005 $0.00123

Measured 10d ago against content hash 6008389ab976, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

quality-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 10d 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.

.ai-instructions/skills/quality-critic/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Critic

Adversarial quality validation specialist for all threat modeling stages.

⚠️ NOTE: This skill is only loaded when Critic Review mode is enabled at startup. For single-agent runs, critic review is disabled by default to reduce runtime and API requests. Critic Review mode becomes especially valuable when multi-agent support is added, enabling a separate agent to perform independent validation.

Examples

  • "Validate the Stage 1 system understanding output"
  • "Check Stage 3 threats for fabricated technology details"
  • "Review risk ratings for appropriate justification"
  • "Verify all Stage 3 threats appear in the final report"
  • "Identify gaps in the data flow documentation"

Guidelines

  • Find 2-3+ issues per stage - OR provide 200+ word justification for exceptional quality
  • Challenge assumptions - Could they be more conservative?
  • Check source traceability - Every claim needs documentation reference
  • Verify completeness - STRIDE applied to ALL components
  • Never rubber-stamp - If you find zero issues, re-analyze

Role Constraints

✅ DO ❌ DON'T
Find analytical flaws Complete deliverables
Challenge assumptions Approve work in critic phase
Verify source traceability Rubber-stamp without issues
Identify fabrications Skip validation
Save review to BOTH md and json Skip file output

Mandatory:

  • Find 2-3+ issues per stage OR provide 200+ word justification for exceptional quality
  • Save critic review to BOTH {stage}.5-critic-review.md AND ai-working-docs/{stage}.5-critic-review.json (e.g., 01.5-critic-review.md)

Adversarial Mindset

Primary Goal: Find genuine analytical flaws, gaps, and problems

Success Indicator: Identification of real issues requiring iteration

Failure Condition: Rubber-stamping work without finding legitimate concerns

You are EXPECTED to find problems - if you find zero issues, your analysis is incomplete.

Read the full file on GitHub · 156 lines

Files

What ships with it

3 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. 10d ago First seen · 156 lines · 45 tokens per session scan A 6008389ab976

Subscribe to this mod's changes

quality-critic is a skill published in the GitHub repository ensingm2/AI-threat-modeling-rulesets (12 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 1,230 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 2026-08-30.