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 lazysheep-z/apdr-product-design-runtime --skill quality-evaluatorgit clone --depth 1 https://github.com/lazysheep-z/apdr-product-design-runtimeWrote 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/lazysheep-z/apdr-product-design-runtime/quality-evaluator)<a href="https://agentmods.dev/skills/lazysheep-z/apdr-product-design-runtime/quality-evaluator"><img src="https://agentmods.dev/badge/skills/lazysheep-z/apdr-product-design-runtime/quality-evaluator/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/lazysheep-z/apdr-product-design-runtime/quality-evaluator"><img src="https://agentmods.dev/badge/skills/lazysheep-z/apdr-product-design-runtime/quality-evaluator.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 | $0.00026 | $0.00669 |
| Opus 5 | $0.00013 | $0.00334 |
| Sonnet 5 | $0.00005 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
apdr-quality-evaluator 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 11d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality Evaluator (APDR)
Pipeline stage: quality_eval. Requires: HandoffDoc (and all upstream artifacts).
This stage runs two evaluation capabilities that were registered but never implemented:
Capability 1: eval.artifact.quality
For each artifact in the project, run a rubric-based quality check:
| Artifact Type | Rubric Dimensions |
|---|---|
| ProjectBrief | Problem clarity, goal alignment, persona completeness, constraint coverage |
| RequirementsAnalysis | JTBD completeness, risk identification, assumption flagging, open question quality |
| PRD | Feature completeness, AC testability, priority clarity, dependency mapping |
| UserFlows | Happy path clarity, error path coverage, permission coverage, diagram quality |
| InformationArchitecture | Sitemap completeness, navigation logic, URL consistency, content type coverage |
| Wireframes | Page coverage, layout structure, state coverage (default/error/loading/empty) |
| UIDesignSpec | Token completeness, component coverage, accessibility consideration, responsive planning |
| DesignReviewReport | Issue completeness, fix confirmation, pass/fail correctness |
| CodeBundle | Structure, naming, accessibility attributes, responsive implementation |
| CodeIntelligenceReport | Index completeness, route/component coverage vs CodeBundle |
| HandoffDoc | Component docs completeness, build instructions clarity, API contract coverage |
| DecisionRecords | ADR coverage (all critical stages), ADR quality (context+decision+consequences), numbering consistency |
For each artifact:
- Score 0-10 on each rubric dimension
- List specific issues found
- Calculate overall score (percentage)
Capability 2: eval.coverage.feature_flow
Cross-reference PRD features against downstream artifacts:
- get_latest_artifact: PRD, UserFlows, Wireframes, UIDesignSpec
- For each PRD feature:
- Check UserFlows, Wireframes, UIDesignSpec coverage (existing)
- Check CodeIntelligenceReport.routes / .components for implementation signals
- Does it have a corresponding UserFlow? (yes/no)
- Does it have Wireframe pages? (yes/no)
- Does it map to UIDesignSpec components? (yes/no)
- Report coverage gaps: features missing flows, flows missing wireframes, wireframes missing components
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.
- 11d ago First seen · 65 lines · 26 tokens per session scan A 76984e417692
apdr-quality-evaluator is a skill published in the GitHub repository lazysheep-z/apdr-product-design-runtime (2 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 669 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
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.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…