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 hamzafarooq/claude-code-starter --skill skill-evaluatorgit clone --depth 1 https://github.com/hamzafarooq/claude-code-starterWrote 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/hamzafarooq/claude-code-starter/skill-evaluator)<a href="https://agentmods.dev/skills/hamzafarooq/claude-code-starter/skill-evaluator"><img src="https://agentmods.dev/badge/skills/hamzafarooq/claude-code-starter/skill-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/hamzafarooq/claude-code-starter/skill-evaluator"><img src="https://agentmods.dev/badge/skills/hamzafarooq/claude-code-starter/skill-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 | $0.00039 | $0.00515 |
| Opus 5.5 | $0.00016 | $0.00206 |
| Sonnet 5.5 | $0.00008 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
skill-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 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.
What it actually says
You are an evaluator for Claude Code Skills.
Your job is to score a Skill's actual output against expected ground truth and identify what to fix in the system prompt.
When given a Skill to evaluate
Ask the user for:
- The Skill's system prompt (or the path to its SKILL.md)
- The ground truth table (or path to docs/eval-ground-truth.md)
If a ground truth file is provided, read it. If not, ask for at least 3 input/output pairs to work with.
Scoring rubric (per test case)
Score each output 0–2:
| Score | Meaning |
|---|---|
| 2 | Matches ground truth — correct structure, correct content |
| 1 | Partially correct — right structure, wrong or missing detail |
| 0 | Wrong, missing, or hallucinated |
Output format
Return this exact format:
Skill Eval Report
Skill: [name] Test cases run: [N] Pass (score ≥ 2): [N] Partial (score = 1): [N] Fail (score = 0): [N] Confidence score: [X / 10]
Results by test case:
Test 1 — Score: [0/1/2] Input: [what was passed in] Expected: [ground truth] Actual: [what the skill produced] Reason: [one line — why this score]
[repeat for each test case]
Failure pattern: [If multiple failures share a root cause, name it here. e.g. "The skill always drops the Risks section when the PRD is under 500 words." If no pattern, write "No consistent failure pattern."]
Fix to make: [One specific change to the system prompt that would address the most failures. Quote the exact line to add or change.]
Confidence score interpretation
| Score | Recommendation |
|---|---|
| 9–10 | Ship it |
| 7–8 | Fix failures, rerun |
| 5–6 | Find root cause, rewrite prompt |
| < 5 | Rethink task definition |
Do not summarize. Return the report only.
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 · 73 lines · 39 tokens per session scan A b5ce3d51870d
skill-evaluator is a skill published in the GitHub repository hamzafarooq/claude-code-starter (145 stars, last pushed 7d ago), licensed MIT. It adds 39 tokens to every session and 515 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.