agentmods.dev

spec-driven-development-template AGENTS.md

Repository instructions for a template that supports spec-driven development, a workflow where written requirements guide implementation and checks. It includes rules for reading the guides and using a compact spec folder in real projects.

In plain words
What is it for?
Use it when applying this repository’s development process to a real project. It guides setup of the spec sidecar, reading of the required documents, and use of the base repository as a reference.
Why use it?
It prevents developers from copying an entire template repository into a project when only its guidance is needed. It also establishes the required order of reading and the expected workflow.

Instructions file for CodexOpenCode

15 +1 2d ago A scan 2,681 tokens original MIT
View the source file juanklagos/spec-driven-development-template
Install

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.

agentmods
npx agentmods add instructions/juanklagos/spec-driven-development-template/agents-md
Clone the repo
git clone --depth 1 https://github.com/juanklagos/spec-driven-development-template

Made for: Codex, OpenCode.

Per session 2,681 This file is loaded in full into every session.
When invoked 2,681 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02681 $0.02681
Opus 5 $0.01340 $0.01340
Sonnet 5 $0.00536 $0.00536
Haiku 4.5 $0.00268 $0.00268

Measured 2d ago against content hash 1f91ace68c76, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-driven-development-template AGENTS.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 2d 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.

AGENTS.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🤖 Instructions for any AI tool / Instrucciones para cualquier herramienta de IA

Mandatory repository rule / Regla obligatoria del repositorio

Cloning is optional. The mandatory requirement is to work with this repository template and guides as the primary reference.

Clonar es opcional. Lo obligatorio es trabajar con este template y sus guías como referencia principal.

Default target-project rule / Regla por defecto para proyecto destino:

  • EN: Do not clone or copy this full repository into the user's project unless the user explicitly asks for a full standalone workspace.
  • ES: No clones ni copies este repositorio completo dentro del proyecto del usuario salvo que el usuario pida explícitamente un workspace standalone completo.
  • EN: For real projects, install only the compact spec/ sidecar and keep project code in the project root.
  • ES: Para proyectos reales, instala solo el sidecar compacto spec/ y mantén el código del proyecto en la raíz del proyecto.

Quick start for AI tools / Inicio rápido para herramientas de IA:

  • AGENT_OPERATING_SYSTEM.md
  • sdd.policy.yaml
  • INSTRUCTIONS.md
  • AI_START_HERE.md
  • template-context/README.md
  • template-context/01-PURPOSE.md
  • template-context/02-AI-OPERATING-RULES.md
  • template-context/03-FAST-ENTRY-FLOWS.md
  • template-context/04-ANTI-MISUSE.md
  • template-context/05-SDD-EXECUTION-GATE.md
  • template-context/06-AI-RULES-MATRIX.md
  • template-context/07-AI-HANDOFF-CHECKLIST.md
  • docs/es/10-agentes-ia-soportados-y-prompts.md
  • docs/en/10-supported-ai-agents-and-prompts.md

Repository context lock / Bloqueo de contexto del repositorio

  • EN: Treat this repository as a starter template, not as a single in-progress product.
  • ES: Trata este repositorio como un template de arranque, no como un único producto en desarrollo.

Before implementation tasks, explicitly determine:

  1. If the task is template maintenance or target project execution.
  2. The real target project path when execution is for a user project.
  3. The active specification in that target project.
  4. Default to the compact spec/ sidecar for target projects.
  5. Use www/<project-name>/ only as the clean container when the target project should live inside this repository.
  6. If the target project lives inside this repository, keep it under www/ to avoid mixing framework and product work.

Read the full file on GitHub · 247 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. 2d ago First seen · 247 lines · 2,681 tokens per session scan A 1f91ace68c76

Subscribe to this mod's changes

spec-driven-development-template AGENTS.md is an instructions file published in the GitHub repository juanklagos/spec-driven-development-template (15 stars, last pushed 2d ago), licensed MIT. It adds 2,681 tokens to every session, about $0.0134 per session on Opus 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.

Developer WorkflowPlanningai-agentsai-developmentgithub-templateproject-templatesoftware-architecture
Related

Other instructions, from other repositories

AIAgentMinder CLAUDE.md

Instructions for lwalden/AIAgentMinder, covering claude.md - project instructions, project identity, current state, git / pr state — verify, don't assume and behavioral rules.

lwalden/AIAgentMinder · 570 tokens

aider-desk AGENTS.md

AGENTS.md instructions for hotovo/aider-desk, covering agents.md, common commands, development, type checking and linting and formatting.

hotovo/aider-desk · 1,725 tokens

neurolink CLAUDE.md

Instructions for juspay/neurolink, covering claude.md, project overview, critical rules, architecture and pattern: factory + registry.

juspay/neurolink · 10,386 tokens

FrameCode-VibeWork AGENTS.md

Instructions for Sistema2D/FrameCode-VibeWork, covering agents.md, instruction order, reading-trigger rule, regression rule and when a plan is required.

Sistema2D/FrameCode-VibeWork · 1,416 tokens

EndiorBot CLAUDE.md

Instructions for Minh-Tam-Solution/EndiorBot, a project described as: Local-first AI agent orchestrator for SDLC workflows — 14 role-based agents, 5 channels, 39 unified commands. Tool-agnostic. MIT.

Minh-Tam-Solution/EndiorBot · 19 tokens

scaffold AGENTS.md

Instructions for howells/scaffold, covering scaffold, what a new project takes from here, generated surfaces - never hand-edit, editing this repo and commands.

howells/scaffold · 711 tokens