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 cembasaranoglu/crafting-system-claude --skill prompt-test-harnessgit clone --depth 1 https://github.com/cembasaranoglu/crafting-system-claudeWrote 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/cembasaranoglu/crafting-system-claude/prompt-test-harness)<a href="https://agentmods.dev/skills/cembasaranoglu/crafting-system-claude/prompt-test-harness"><img src="https://agentmods.dev/badge/skills/cembasaranoglu/crafting-system-claude/prompt-test-harness/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/cembasaranoglu/crafting-system-claude/prompt-test-harness"><img src="https://agentmods.dev/badge/skills/cembasaranoglu/crafting-system-claude/prompt-test-harness.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 | $0.00019 | $0.00081 |
| Opus 5 | $0.00010 | $0.00041 |
| Sonnet 5 | $0.00004 | $0.00016 |
| Haiku 4.5 | $0.00002 | $0.00008 |
Grade A, and why
prompt-test-harness 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 8d 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
prompt-test-harness
Use source-first, evidence-led execution. Separate facts, assumptions, recommendations, unknowns, blockers, not-run, failed, and validated. Do not claim validation or mutate external systems unless explicitly authorized. Produce named artifacts and cite source paths when possible.
What ships with it
6 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.
- references/00_claude_base_prompt_execution_addendum.md 1.8 KB
- references/00_claude_base_prompt.md 19 KB
- references/119_test_seam_refactor.md 1.9 KB
- references/13_codebase_search_and_answer_prompt.md 4.0 KB
- references/159_prompt_glossary_catalog_maintainer.md 1.6 KB
- references/160_claude_tuning_playbook_prompt.md 1.6 KB
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.
- 8d ago First seen · 8 lines · 19 tokens per session scan A 178c7b95afdc
prompt-test-harness is a skill published in the GitHub repository cembasaranoglu/crafting-system-claude (5 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 81 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 2026-09-03.
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.
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".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
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.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.