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 HeshamFS/materials-simulation-skills --skill skill-evaluatorgit clone --depth 1 https://github.com/HeshamFS/materials-simulation-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/heshamfs/materials-simulation-skills/skill-evaluator)<a href="https://agentmods.dev/skills/heshamfs/materials-simulation-skills/skill-evaluator"><img src="https://agentmods.dev/badge/skills/heshamfs/materials-simulation-skills/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/heshamfs/materials-simulation-skills/skill-evaluator"><img src="https://agentmods.dev/badge/skills/heshamfs/materials-simulation-skills/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 | $0.00181 | $0.03287 |
| Opus 5.5 | $0.00072 | $0.01315 |
| Sonnet 5.5 | $0.00036 | $0.00657 |
| Haiku 4.5 | $0.00018 | $0.00329 |
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 6d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Evaluator
Test whether a skill is correct, discoverable, and valuable — not just whether its unit tests pass. The harness is agent-agnostic: it drives whichever coding-agent CLI the user uses, because Agent Skills are portable across all of them.
When to use which layer
Three layers, increasing cost and fidelity (full rationale in
references/methodology.md):
| Layer | Question | Script | Needs a CLI? |
|---|---|---|---|
| 1. Deterministic | Do the scripts emit the documented numbers? | run_script_checks.py |
No |
| 2. Trigger | Does the description activate on the right prompts? | run_trigger_eval.py |
Yes |
| 3. Quality | Does following the SKILL.md beat no skill? | run_quality_eval.py → grade → aggregate_benchmark.py |
Yes |
Always run Layer 1 (it's free). Add Layers 2–3 when you can run a coding-agent CLI.
Step 0 — pick the agent CLI
Ask the user which coding agent they use, then map it to an adapter id. Supported:
claude-code, openai-codex, antigravity (the agy CLI that replaced Gemini
CLI on 2026-06-18), cursor-cli, github-copilot-cli, amp, opencode,
grok-cli. See the full matrix and auth in references/adapters.md, or run:
python scripts/agent_adapters.py list
Confirm the binary is installed and the auth env var is set (the matrix lists it). Before any real run, dry-run it to see the exact command:
python scripts/agent_adapters.py build <agent> --prompt "test" --workdir /tmp/wd
Step 1 — deterministic script checks (always)
python scripts/run_script_checks.py --skill <path-to-skill> --json
Runs the script_checks in the skill's evals/evals.json, executing each script
and grading its --json output against machine-checkable assertions. Exit non-zero
on any failure — safe for CI. If the skill has few/no script_checks, add them for
every eval whose answer is computable (schema in references/schemas.md); this is
the cheapest, most durable guard against doc↔code drift.
What ships with it
13 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.
- CHANGELOG.md 2.6 KB
- eval-viewer/generate_review.py 7.0 KB runs code
- evals/evals.json 5.0 KB
- references/adapters.md 4.2 KB
- references/grader.md 4.3 KB
- references/methodology.md 4.5 KB
- references/schemas.md 3.9 KB
- scripts/_support/evaluation_isolation.py 1.5 KB runs code
- scripts/agent_adapters.py 16 KB runs code
- scripts/aggregate_benchmark.py 8.2 KB runs code
- scripts/run_quality_eval.py 11 KB runs code
- scripts/run_script_checks.py 8.5 KB runs code
- scripts/run_trigger_eval.py 7.5 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.
- 6d ago Changed · +7 lines 65fd5f687bbb
- 1mo ago First seen · 227 lines · 181 tokens per session scan A 3464a5c93a0e
skill-evaluator is a skill published in the GitHub repository HeshamFS/materials-simulation-skills (83 stars, last pushed 7d ago), licensed Apache-2.0. It adds 181 tokens to every session and 3,287 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
sbce
Spec-driven BCE workflow where one capability spec equals one business component (same name) and the spec is the boundary contract. Invoked as /sbce new|apply (or by intent), it drives declare → converge; the stack's own test loop is the oracle for "done". new accepts a BC name or a natural-language feature…
web-system-tests
The web realization of the system-tests contract — browser-driven system tests with Playwright against a running frontend. Owns the project layout (tests/), the Playwright configuration (baseURL plus webServer, cross-engine projects), the role- and label-based selector policy, code coverage as an opt-in second run…
zunit
Generate and run zunit tests for java-cli-app projects. Use when asked to create tests, write tests, add tests, or generate test files for a java-cli-app project. Triggers on "zunit", "write tests", "create tests", "add tests", "test this", "generate tests", or requests to test a java-cli-app application. Also trigger…
ears-tests
Generate parameterized (table-driven) tests from EARS requirement statements — the deterministic transform that turns an SBCE capability spec's ## Requirements into one parameterized test per requirement group and one labeled row per statement id. Stack-neutral; owns only the EARS→table mapping and the spec↔test…
characterization-tests
Pin the observed behavior of a running legacy system as replayable golden masters — record normalized stimulus/observation pairs into migration/characterization/, replay them against the lifted or re-architected system, report behavior diffs. Owns the record/replay/reconcile discipline; the observable surface (HTTP…
simplifier
Replatform mode ("lift, tinker, and shift") — simplify a 1:1-lifted legacy system in place: modernize code and remove external dependencies, one pass at a time, each bracketed by characterization-tests replays, structure preserved. Owns the stack-neutral pass discipline; the transformation catalog and dependency…