Borrowing it
Nothing to install: this file belongs to lksnext-ai-lab/spec-kit-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lksnext-ai-lab/spec-kit-template/main/.github/skills/spec-kit-evidence-pack/SKILL.mdgit clone --depth 1 https://github.com/lksnext-ai-lab/spec-kit-templateWrote 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/lksnext-ai-lab/spec-kit-template/spec-kit-evidence-pack)<a href="https://agentmods.dev/skills/lksnext-ai-lab/spec-kit-template/spec-kit-evidence-pack"><img src="https://agentmods.dev/badge/skills/lksnext-ai-lab/spec-kit-template/spec-kit-evidence-pack/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/lksnext-ai-lab/spec-kit-template/spec-kit-evidence-pack"><img src="https://agentmods.dev/badge/skills/lksnext-ai-lab/spec-kit-template/spec-kit-evidence-pack.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 | $0.00000 | $0.01769 |
| Opus 5.5 | $0.00000 | $0.00708 |
| Sonnet 5.5 | $0.00000 | $0.00354 |
| Haiku 4.5 | $0.00000 | $0.00177 |
Grade A, and why
spec-kit-evidence-pack 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 2mo 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: evidence_pack
Objetivo
Investigar un tema en codebase/** (solo lectura) y producir un Evidence Pack reutilizable para sustentar docs/spec/** sin inventar.
Output: docs/spec/_inputs/evidence/EP-###-<tema>.md (siguiendo el template del repo)
Fuente de verdad (estructura del EP)
Usar SIEMPRE como base:
docs/spec/_inputs/evidence/_TEMPLATE-evidence-pack.md
El Evidence Pack resultante debe mantener exactamente las secciones A–F del template (mismo orden, mismos títulos).
Se permiten ampliaciones internas (más bullets/sub-bullets) dentro de A–F, pero no reordenar ni sustituir el esquema.
Principios
- Read-only: no modificar
codebase/**. - Evidencia primero: conclusiones confirmadas siempre con rutas concretas.
- No inventar: si no se confirma, se registra
OPENQ-###. - Separación estricta: confirmado vs inferido vs desconocido.
- Reproducible: registrar cobertura (términos y paths) para poder repetir el análisis.
- Seguro: no copiar valores sensibles (tokens, API keys, credenciales).
EP-###: numeración y naming (regla operativa)
- Elegir el siguiente número disponible (3 dígitos) sin reutilizar:
EP-001-...,EP-038-..., etc.
- Nombre recomendado del fichero:
EP-###-<tema-en-kebab-case>.md
- Si ya existe un EP del mismo tema, crear uno nuevo solo si:
- el alcance es distinto (subtema), o
- la codebase ha cambiado sustancialmente y necesitas “v2”.
Timeboxing (obligatorio)
Quick (20–40 min)
- 3–8 búsquedas
- 3–8 ficheros clave
- 3–8 conclusiones confirmadas
- A/B/C/D con tamaño acotado (ver “límites”)
Deep (60–120 min)
- 8–15 búsquedas
- 8–20 ficheros clave
- 8–15 conclusiones confirmadas
- incluir impacto/riesgos/tests/compatibilidad si aplica
Si se agota el timebox:
- cerrar con confirmadas + OPENQ (sin “rellenar” con inferencias)
Reglas duras (hard rules)
-
Prohibido modificar
codebase/**. -
Evidencia con granularidad
- Cada conclusión confirmada debe incluir:
- ruta
codebase/... - y cuando sea posible: símbolo (clase/función/método) o bloque relevante.
- ruta
- Evitar “evidencia” vaga tipo “mirado el repo”.
- Cada conclusión confirmada debe incluir:
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.
- 2mo ago First seen · 208 lines · 0 tokens per session scan A 0263c9aa45f8
spec-kit-evidence-pack is a skill published in the GitHub repository lksnext-ai-lab/spec-kit-template (5 stars, last pushed 8mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,769 tokens. 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.
spec-kit-evidence-pack compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| spec-kit-evidence-packlksnext-ai-lab/spec-kit-template | Skill | 5 | 8mo ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| plan-authoringattilaszasz/sdd-pilot | Skill | 97 | 17d ago | MIT | A | 41 | Claude Code, Codex |
| task-generationattilaszasz/sdd-pilot | Skill | 97 | 17d ago | MIT | A | 35 | Claude Code, Codex |
| evidence-led-authoringattilaszasz/sdd-pilot | Skill | 97 | 17d ago | MIT | A | 24 | Claude Code, Codex |
| adr-authoringattilaszasz/sdd-pilot | Skill | 97 | 17d ago | MIT | A | 30 | Claude Code, Codex |
| project-guidelines-writerlindoelio/spec-driven-steroids | Skill | 55 | 8d ago | MIT | A | 87 | Claude Code, Codex |
| code-review-hardeninglindoelio/spec-driven-steroids | Skill | 55 | 8d ago | MIT | A | 70 | Claude Code, Codex |