Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Morningstar202604/awesome-skillkitnpx agentmods add skills/morningstar202604/awesome-skillkit/skill-testerWrote 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/morningstar202604/awesome-skillkit/skill-tester)<a href="https://agentmods.dev/skills/morningstar202604/awesome-skillkit/skill-tester"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/skill-tester/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/morningstar202604/awesome-skillkit/skill-tester"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/skill-tester.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 | $0.00126 | $0.02061 |
| Opus 5.5 | $0.00050 | $0.00824 |
| Sonnet 5.5 | $0.00025 | $0.00412 |
| Haiku 4.5 | $0.00013 | $0.00206 |
Grade A, and why
skill-tester 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.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Tester
Use four tools to validate, test, and score the quality of a skill directory (structure validation, script testing, quality scoring, security scoring), all runnable directly from the repo root.
Scope note: this skill's tier line-count thresholds measure legacy skills. When authoring new skills,
engineering/write-a-skill(SKILL.md around 100 lines or fewer, the Matt Pocock principle) is the binding standard — do not pad a new skill just to meet this skill's tier floor.
Input Checklist
| Input | Required | Description |
|---|---|---|
| Path of the skill to audit | Yes | A skill directory in the repo, e.g. skills/programming/api/api-design-reviewer |
| Target minimum score | No | quality_scorer.py --minimum-score; CI commonly uses 75 |
| Target tier | No | skill_validator.py --tier BASIC|STANDARD|POWERFUL; if omitted, inferred from SKILL.md line count |
| Include security scoring? | No | Add --include-security (or run security_scorer.py separately) |
When inputs are missing, ask for them all at once: "Please provide: (1) the path of the skill directory to audit; (2) target minimum score (default 75 if blank); (3) whether security scoring is needed."
Pre-flight Checks
Run each item; if any fails → handle the fix and STOP:
# 1. Python 3 is available
python3 --version
# Expected: Python 3.8+. Failure → install Python 3 and retry.
# 2. The four tool scripts exist
ls skills/programming/ai-engineering/skill-tester/scripts/{skill_validator,script_tester,quality_scorer,security_scorer}.py
# Expected: four .py filenames. Failure → confirm you're running from the repo root; still missing → STOP and report the repo is incomplete.
# 3. The target skill directory exists and contains SKILL.md
cat skills/programming/ai-engineering/skill-tester/examples/good-skill/SKILL.md > /dev/null && echo OK
# Expected: OK. Failure → confirm the correct path with the user, then STOP.
Workflow
Run all commands from the repo root.
What ships with it
16 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.
- assets/sample-skill/assets/sample_text.txt 855 B
- assets/sample-skill/assets/test_data.csv 539 B
- assets/sample-skill/expected_outputs/sample_text_analysis.json 234 B
- assets/sample-skill/README.md 976 B
- assets/sample-skill/scripts/text_processor.py 13 KB runs code
- assets/sample-skill/SKILL.md 5.7 KB
- expected_outputs/sample_validation_report.json 1.8 KB
- README.md 6.7 KB
- references/quality-scoring-rubric.md 20 KB
- references/skill-structure-specification.md 1.6 KB
- references/tier-requirements-matrix.md 1.3 KB
- scripts/quality_scorer.py 14 KB runs code
- scripts/script_tester.py 7.8 KB runs code
- scripts/security_scorer.py 14 KB runs code
- scripts/skill_validator.py 12 KB runs code
- tests/test_security_scorer.py 28 KB runs code
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 Changed · -7 tokens per session ccb91385778e
- 1mo ago Changed · +6 lines d30860f0c4a9
- 1mo ago Changed · +48 lines · +39 tokens per session 1ca77fb2d8a0
- 1mo ago First seen · 98 lines · 94 tokens per session scan A 390a8d9d2ace
skill-tester is a skill published in the GitHub repository Morningstar202604/awesome-skillkit (0 stars, last pushed 25d ago), licensed Apache-2.0. It adds 126 tokens to every session and 2,061 once invoked, about $0.0005 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
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
golang-testing
Go testing best practices including table-driven tests, test helpers, benchmarking, race detection, coverage analysis, and integration testing patterns. Use when writing or improving Go tests.
verification-loop
A comprehensive verification system for Claude Code sessions. Use when verifying a Claude Code session's work before claiming it is complete.
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
darwinian-evolver
Evolve prompts/regex/SQL/code with Imbue's evolution loop.