agentmods.dev

spec-kit-template: Instructions file for GitHub Copilot

.github/instructions/spec.instructions.md

spec-kit-template spec.instructions.md is an instructions file for GitHub Copilot from lksnext-ai-lab/spec-kit-template. It costs 895 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for maintaining software specifications in the lksnext-ai-lab/spec-kit-template project. It defines rules for open questions, pending work, plans, evidence, and traceability.

In plain words
What is it for?
Writing and reviewing documents under docs/spec/, managing iteration plans and question or task IDs, linking claims to code evidence, and keeping changes focused.
Why use it?
It gives project contributors a consistent way to record what is known, what remains unresolved, and why technical claims are supported. It also helps prevent unfinished work from being treated as ready.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is lksnext-ai-lab/spec-kit-template's own configuration. It tells GitHub Copilot how to work on spec-kit-template itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything spec-kit-template configures →

not rated 5repo 8mo ago A scan 895 tokens original Apache-2.0
View source ↗ lksnext-ai-lab/spec-kit-template
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/instructions/spec.instructions.md
Clone the repo
git clone --depth 1 https://github.com/lksnext-ai-lab/spec-kit-template

Made for: GitHub Copilot.

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.

agentmods badge for spec-kit-template spec.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lksnext-ai-lab/spec-kit-template/spec/github.svg)](https://agentmods.dev/instructions/lksnext-ai-lab/spec-kit-template/spec)
Your own site
<a href="https://agentmods.dev/instructions/lksnext-ai-lab/spec-kit-template/spec"><img src="https://agentmods.dev/badge/instructions/lksnext-ai-lab/spec-kit-template/spec/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.

agentmods 80×15 button for spec-kit-template spec.instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lksnext-ai-lab/spec-kit-template/spec"><img src="https://agentmods.dev/badge/instructions/lksnext-ai-lab/spec-kit-template/spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 895 This file is loaded in full into every session.
When invoked 895 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00895 $0.00895
Opus 5.5 $0.00358 $0.00358
Sonnet 5.5 $0.00179 $0.00179
Haiku 4.5 $0.00089 $0.00089

Measured 2mo ago against content hash 44aee18d6737, 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-template spec.instructions.md 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/instructions/spec.instructions.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SPEC instructions (docs/spec/**)

Estas instrucciones aplican a la especificación viva en docs/spec/**.

Reglas duras (SPEC)

  1. No inventar. Si falta info, registrar:
    • OPENQ-### en docs/spec/95-open-questions.md
    • TODO-### en docs/spec/96-todos.md si es trabajo pendiente (no pregunta)
  2. Ignorar histórico. docs/spec/history/** se considera histórico:
    • Por defecto, no leer ni editar para Plan/Write/Review.
    • Solo se usa al cerrar iteración.
  3. Plan de iteración activa.
    • docs/spec/01-plan.md representa una única iteración activa.
    • IDs del plan: P01..Pnn (Pxx).
    • No usar Txx en 01-plan.md (Txx es implementación).
  4. Cambios diff-friendly.
    • Evitar reescrituras masivas.
    • No reordenar secciones por estética.
    • Modificar solo lo necesario para cumplir DoD.
  5. Sin shell destructivo. No ejecutar borrados/limpiezas.
  6. Modo evolutivo (si existe codebase/**).
    • codebase/** es solo lectura y fuente de verdad as-is.
    • La spec puede describir to-be, pero no se debe inventar el as-is.
    • Afirmaciones técnicas relevantes deben tener:
      • evidencia (rutas codebase/...) o
      • Evidence Pack en docs/spec/_inputs/evidence/EP-###-<tema>.md
      • o OPENQ explícita si no se puede verificar.
  7. Edición directa y limpieza de temporales. Usar herramientas de edición directa para modificar archivos de spec. No generar scripts para aplicar cambios. Si un agente crea archivos auxiliares/temporales, eliminarlos inmediatamente tras su uso (o confirmar con el usuario si deben persistir).

STOP policy (anti-falso-ready)

Si se está redactando o revisando algo crítico y no hay evidencia suficiente:

  • auth/roles/permissions
  • secretos/api keys
  • datos sensibles/modelo
  • integraciones críticas
  • NFR críticos (seguridad, auditoría, trazabilidad, disponibilidad, etc.)

Entonces:

  1. Registrar OPENQ-### con impacto (BLOCKER/MAJOR/MINOR) y qué falta para cerrar.
  2. En el documento, marcar el punto con OPENQ: y enlazar el ID.
  3. Si existe plan con estado, marcar la tarea como BLOCKED (solo esa fila).

Read the full file on GitHub · 81 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.

  1. 2mo ago First seen · 81 lines · 895 tokens per session scan A 44aee18d6737

Subscribe to this mod's changes

spec-kit-template spec.instructions.md is an instructions file published in the GitHub repository lksnext-ai-lab/spec-kit-template (5 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 895 tokens to every session, about $0.0036 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.

Planning
Related

spec-kit-template spec.instructions.md compared with instructions from other repositories

spec-kit-template spec.instructions.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
spec-kit-template spec.instructions.mdlksnext-ai-lab/spec-kit-templateInstructions file58mo agoApache-2.0A895GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode