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 skills add ensingm2/AI-threat-modeling-rulesets --skill quality-criticgit clone --depth 1 https://github.com/ensingm2/AI-threat-modeling-rulesetsWrote 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/ensingm2/ai-threat-modeling-rulesets/quality-critic)<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.
<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>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 | $0.00045 | $0.01230 |
| Opus 5 | $0.00023 | $0.00615 |
| Sonnet 5 | $0.00009 | $0.00246 |
| Haiku 4.5 | $0.00005 | $0.00123 |
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.
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.mdANDai-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.
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.
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.
- 10d ago First seen · 156 lines · 45 tokens per session scan A 6008389ab976
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.