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 hajekim/agentic-design-patterns-skills --skill evaluationgit clone --depth 1 https://github.com/hajekim/agentic-design-patterns-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/skills/hajekim/agentic-design-patterns-skills/evaluation)<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-skills/evaluation"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/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/skills/hajekim/agentic-design-patterns-skills/evaluation"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/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 | $0.00387 | $0.04405 |
| Opus 5.5 | $0.00155 | $0.01762 |
| Sonnet 5.5 | $0.00077 | $0.00881 |
| Haiku 4.5 | $0.00039 | $0.00441 |
Grade A, and why
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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- evaluation — 100% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluation & Monitoring Pattern
Overview
The Evaluation & Monitoring Pattern establishes systematic methods for measuring agent quality, detecting degradation, and maintaining performance standards over time. Without evaluation, you cannot know if your agent is actually working correctly — and without monitoring, you won't know when it stops working.
Core Principle: You can't improve what you don't measure — define quality metrics before deployment, not after problems surface.
When This Skill Applies
Activate this pattern when:
- An agent is being deployed to production and performance must be tracked
- Agent behavior needs to be compared before and after changes
- Hallucination rates, accuracy, or helpfulness must be measured quantitatively
- A/B testing of different agent configurations is needed
- Regulatory compliance requires audit trails and performance documentation
- You need to detect agent drift or degradation over time
Rule of thumb: Every production agent needs evaluation and monitoring — this isn't optional, it's how you know the agent is doing its job.
Evaluation Dimensions
| Dimension | What It Measures | Evaluation Method |
|---|---|---|
| Correctness | Is the answer right? | Ground truth comparison, expert review |
| Faithfulness | Are claims grounded in context? | RAG evaluation, hallucination detection |
| Relevance | Does response address the question? | LLM-as-judge, human ratings |
| Completeness | Are all aspects covered? | Checklist evaluation |
| Safety | Is output appropriate/harmless? | Safety classifier, policy compliance |
| Latency | How fast does the agent respond? | P50/P95/P99 timing metrics |
| Cost | What is the per-query cost? | Token counting, API cost tracking |
DEFINE → PLAN → ACTION Workflow
DEFINE
Establish evaluation requirements:
- What does "good" mean for this specific agent? (Domain-specific criteria)
- What ground truth data is available? (Golden datasets, human labels)
- What metrics matter most? (Accuracy, safety, cost, latency — prioritize)
- How frequently should the agent be evaluated? (Continuous vs. periodic)
- What triggers a production alert? (Threshold-based, anomaly-based)
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.
- 1mo ago First seen · 458 lines · 387 tokens per session scan A 9b7c11961e6d
evaluation is a skill published in the GitHub repository hajekim/agentic-design-patterns-skills (4 stars, last pushed 6mo ago), licensed MIT. It adds 387 tokens to every session and 4,405 once invoked, about $0.0015 per session on Opus 5.5. 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
impact-audit
Blast radius of a change you have not made yet -- traces a symbol across federated repositories, splits impact per repo, and reports what must ship together.
onboard-repo
Index an unfamiliar codebase into the knowledge graph, then produce a first orientation map -- entry points, most-depended-upon modules, hotspots, test topology.
codeck
Keep Codex as the host. Use Codeck when the user explicitly asks to call Agy/AGY, Antigravity, Gemini, Claude, Kimi, Grok, Codeck, or another configured external executor. These names mean external Codeck executors, never internal Codex subagents. Build a compact task-specific brief, call that specialist, and return…
prompt-optimizer
Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite…
python-patterns
Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.
openclaw-persona-forge
A persona-design guide for OpenClaw agents, including their identity, personality, boundaries, names, and avatar prompts. OpenClaw is the specific agent platform this guide targets.