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.
npx agentmods add instructions/juanklagos/spec-driven-development-template/copilot-instructionsgit clone --depth 1 https://github.com/juanklagos/spec-driven-development-templateWhat 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 | $0.00493 | $0.00493 |
| Opus 5 | $0.00246 | $0.00246 |
| Sonnet 5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
spec-driven-development-template copilot-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 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.
What it actually says
GitHub Copilot Instructions - SDD Template
Canonical source:
template-context/core-instructions/AGENT_OPERATING_SYSTEM.mdsdd.policy.yaml
Hard stop:
- No code before approved spec and consistent plan.
- No hay código sin spec aprobada y plan consistente.
Execution workspace:
- Inside THIS template repository, put runnable code under
www/<project-name>/. - For a project that already exists somewhere else — the common case — install the compact
spec/sidecar in it and leave the code where it is. That is the recommended default workspace for real work. - Dentro de ESTA plantilla, el código ejecutable va en
www/<nombre-proyecto>/. - Para un proyecto que ya existe en otro sitio —el caso normal— instala el sidecar compacto
spec/y deja el código donde está. Ese es el espacio de trabajo recomendado por defecto para el trabajo real. - The user may choose another target path.
- If the target project lives inside this template, keep it under
www/. - For real external projects, install the compact
spec/sidecar and keep code in the project root. - Para proyectos reales externos, instala el sidecar compacto
spec/y mantén el código en la raíz del proyecto.
Required behavior:
- Treat this repository as a starter template, not a product backlog.
- Read
AI_START_HERE.md,idea/IDEA_GENERAL.md,specs/INDEX.mdfirst. - Work from one active specification.
- If gate is not met, refine docs (
spec,plan,tasks,history,bitacora) only. - Keep traceability in
history.md,specs/INDEX.md, andbitacora/. - Record a decision in
bitacora/decisiones/YYYY-MM-DD-<slug>.mdwhen it chose between real alternatives, will be expensive to reverse, or a future reader would ask "why is it like this?". Include a "when to revisit" section, source every rationale (commit,file:line, spec history, CHANGELOG,idea/), and never invent one.
Validation commands:
./scripts/validate-sdd.sh . --strict./scripts/check-sdd-policy.sh ../scripts/check-sdd-gate.sh .
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.
- 2d ago First seen · 33 lines · 493 tokens per session scan A 32dff9310abd
spec-driven-development-template copilot-instructions.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 493 tokens to every session, about $0.0025 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.
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.
aider-desk AGENTS.md
AGENTS.md instructions for hotovo/aider-desk, covering agents.md, common commands, development, type checking and linting and formatting.
neurolink CLAUDE.md
Instructions for juspay/neurolink, covering claude.md, project overview, critical rules, architecture and pattern: factory + registry.
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.
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.
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.