What is spec-kit-security-baseline?

A security-planning guide for documenting how a software product handles identity, permissions, sensitive data, secrets, audits, integrations, and common threats.

Use it to define or review authentication, access rules, data protection, audit records, API controls, and threat-to-mitigation checks.

It helps make security expectations clear and checkable without assuming protections that have not been decided.

How lksnext-ai-lab/spec-kit-template configures Claude Code and Codex

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/lksnext-ai-lab/spec-kit-template/main/.github/skills/spec-kit-security-baseline/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/lksnext-ai-lab/spec-kit-template

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lksnext-ai-lab/spec-kit-template/spec-kit-security-baseline/github.svg)](https://agentmods.dev/skills/lksnext-ai-lab/spec-kit-template/spec-kit-security-baseline)

Your own site

<a href="https://agentmods.dev/skills/lksnext-ai-lab/spec-kit-template/spec-kit-security-baseline"><img src="https://agentmods.dev/badge/skills/lksnext-ai-lab/spec-kit-template/spec-kit-security-baseline/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lksnext-ai-lab/spec-kit-template/spec-kit-security-baseline"><img src="https://agentmods.dev/badge/skills/lksnext-ai-lab/spec-kit-template/spec-kit-security-baseline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,820 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00064	$0.01820
Opus 5.5	$0.00026	$0.00728
Sonnet 5.5	$0.00013	$0.00364
Haiku 4.5	$0.00006	$0.00182

Measured 2mo ago against content hash 458ae2629060, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spec-kit-security-baseline 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.

.github/skills/spec-kit-security-baseline/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Security Baseline (spec-kit)

Objetivo

Dejar docs/spec/80-seguridad.md en un estado operable y verificable para MVP:

AuthN (autenticación, sesiones/tokens)
AuthZ (modelo, reglas por recurso)
Protección de datos y secretos
Auditoría / trazabilidad de acciones sensibles
Controles de API e integraciones
Threat-lite (amenazas → mitigaciones → verificación/evidencia)

Archivos que se pueden modificar

Primario: docs/spec/80-seguridad.md
Si aplica:
- docs/spec/11-requisitos-tecnicos-nfr.md (NFRs de seguridad verificables/medibles)
- docs/spec/90-infra.md (secretos, hardening, retenciones operativas)
- docs/spec/40-arquitectura.md (impactos y patrones)
- docs/spec/adr/ADR-*.md (trade-offs)
- docs/spec/95-open-questions.md (gaps críticos)
- docs/spec/96-todos.md (pendientes no bloqueantes)

No tocar otros ficheros salvo petición explícita.

Reglas duras (anti-deriva)

No inventar

No asumir MFA/SSO, RBAC/ABAC, cifrado en reposo, retenciones, herramientas, ni niveles de logging si no están definidos.
Si falta info que condiciona el diseño/aceptación: OPENQ: (no rellenar).

No secretos / no datos sensibles

Nunca incluir valores reales (keys, tokens, passwords, certificados) ni datos personales en ejemplos.
Regla de logs/errores: no deben exponer secretos ni datos sensibles (si aplica, declararlo como control + verificación).

Vendor-neutral por defecto

Describir patrones (OIDC, secrets manager, rate limiting) sin imponer proveedor/stack salvo evidencia explícita.

Deny-by-default

Por defecto, sin permiso explícito → acceso denegado.
Excepciones solo si están justificadas y evidenciadas.

Trade-offs relevantes → ADR

Ej.: RBAC vs ABAC, scopes vs permisos granulares, auditoría detallada vs coste/privacidad, cifrado en reposo MVP vs fase 2, estrategia rotación.

Clasificación: requerido vs recomendado En el documento, marcar explícitamente cada control como:

REQUERIDO (evidenciado o exigido por FR/NFR/ADR)
RECOMENDADO (baseline sugerido)
TBD/OPENQ (falta decisión o datos)

Read the full file on GitHub · 155 lines

Changes

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 · 155 lines · 64 tokens per session scan A 458ae2629060

Subscribe to this mod's changes

spec-kit-security-baseline 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 adds 64 tokens to every session and 1,820 once invoked, about $0.0003 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.