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.
git clone --depth 1 https://github.com/Owl-Listener/ai-design-skillsWrote 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/commands/owl-listener/ai-design-skills/run-evaluation)<a href="https://agentmods.dev/commands/owl-listener/ai-design-skills/run-evaluation"><img src="https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/run-evaluation/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/commands/owl-listener/ai-design-skills/run-evaluation"><img src="https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/run-evaluation.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 | $0.00012 | $0.00432 |
| Opus 5 | $0.00006 | $0.00216 |
| Sonnet 5 | $0.00002 | $0.00086 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
run-evaluation 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.
What it actually says
You are running a structured evaluation of an AI feature. Use only skills from the evaluation plugin. Follow this process:
Step 1: Define the Evaluation Scope
- What feature is being evaluated?
- What inputs will you evaluate on? (provide sample inputs or describe the input distribution)
- What rubric will you use? (use existing or create one using output-quality-rubrics)
Step 2: Evaluate Output Quality
Using output-quality-rubrics:
- Score each output against the rubric dimensions
- Calculate overall quality scores
- Identify patterns in low-scoring dimensions
Step 3: Assess Task Success
Using task-success-metrics:
- For each output, assess whether it would help the user accomplish their actual goal
- Note cases where quality is high but task success is low (or vice versa)
- Calculate task success rate across the evaluation set
Step 4: Classify Failures
Using failure-taxonomy:
- For each low-quality output, classify the failure type
- Count failure types and identify the most common
- Assess severity for each failure
Step 5: Check Satisfaction Signals
Using user-satisfaction-signals:
- If real user data is available, examine satisfaction signals for this feature
- Identify which quality issues correlate with negative satisfaction signals
- Note any satisfaction signals that don't correspond to quality issues (and vice versa)
Step 6: Run Heuristic Check
Using heuristic-evaluation-ai:
- Evaluate the feature against AI-adapted heuristics
- Identify usability issues beyond output quality
- Note interaction design problems that affect the overall experience
Output
Deliver a complete evaluation report:
- Evaluation summary with overall scores
- Dimension-by-dimension quality analysis
- Task success assessment
- Failure classification breakdown
- Heuristic evaluation findings
- Top 5 issues ranked by impact
- Specific recommendations for each issue
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 · 45 lines · 12 tokens per session scan A 1708f5875719
run-evaluation is a command published in the GitHub repository Owl-Listener/ai-design-skills (172 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 432 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.