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/igoruehara/spec-drivennpx agentmods add skills/igoruehara/spec-driven/evalsWrote 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/igoruehara/spec-driven/evals)<a href="https://agentmods.dev/skills/igoruehara/spec-driven/evals"><img src="https://agentmods.dev/badge/skills/igoruehara/spec-driven/evals/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/igoruehara/spec-driven/evals"><img src="https://agentmods.dev/badge/skills/igoruehara/spec-driven/evals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.00363 |
| Opus 5.5 | $0.00022 | $0.00145 |
| Sonnet 5.5 | $0.00011 | $0.00073 |
| Haiku 4.5 | $0.00006 | $0.00036 |
Grade A, and why
evals 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
Skill: Evals de fidelidade spec→código
Mede se o que foi construído reflete a spec — a métrica de qualidade da saída do agente. Duas camadas: determinística (script) e de julgamento.
1. Camada determinística
node scripts/eval-spec-fidelity.mjs .
Reporta, por feature: AC totais, cobertos por task, referenciados em teste/código e SPEC_DEVIATION abertos. Falha (exit 1) se algum AC não tem task — rastreabilidade quebrada. Referência em teste é aviso até a feature ser implementada.
2. Camada de julgamento (o script não pega isso)
- O teste de cada
AC-Nrealmente exercita o Given/When/Then — ou só cita o ID num teste vazio? - A implementação cobre os casos de borda e respeitou o "Fora de escopo" da spec?
- Os
SPEC_DEVIATIONabertos têm resolução (corrigir código ou atualizar a spec/ADR)?
Saída
Score por feature + os gaps. Complementa o /validar (UAT de uma feature) com uma visão de
fidelidade do portfólio. O mesmo eval roda na CI (esteira.yml) — aqui é o complemento com julgamento.
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 · 27 lines · 55 tokens per session scan A d755c86570b3
evals is a skill published in the GitHub repository igoruehara/spec-driven (213 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 363 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 2026-08-30.
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.