intent-driven-template AGENTS.md

Project instructions for an intent-driven development template, a software workflow built around written specifications and design records. It includes architecture diagrams, Gherkin scenarios, TDD, adversarial review by multiple models, a domain glossary, and reusable engineering workflows.

In plain words
What is it for?
Use it when working with OpenSpec or OpenCode projects that need proposals, architecture records, behavior scenarios, test-driven development, and controlled change workflows.
Why use it?
It gives agents rules for handling specification changes, including proposal, implementation, verification, and archiving steps with required Git discipline.

Instructions file for CodexOpenCode

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/intent-driven-dev/intent-driven-template/agents-md
Clone the repo
git clone --depth 1 https://github.com/intent-driven-dev/intent-driven-template

Made for: Codex, OpenCode.

Per session 42 This file is loaded in full into every session.
When invoked 42 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 $0.00042 $0.00042
Opus 5 $0.00021 $0.00021
Sonnet 5 $0.00008 $0.00008
Haiku 4.5 $0.00004 $0.00004

Measured yesterday against content hash 492918f3fd8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

intent-driven-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 yesterday.

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 · 4 lines

What it actually says

AGENTS.md

  • For OpenSpec propose/apply/verify/archive workflows, use the local openspec-git-discipline skill to enforce proposal commits before apply and merge-before-archive discipline.
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. yesterday First seen · 4 lines · 42 tokens per session scan A 492918f3fd8f

Subscribe to this mod's changes

intent-driven-template AGENTS.md is an instructions file published in the GitHub repository intent-driven-dev/intent-driven-template (121 stars, last pushed 8d ago), licensed MIT. It adds 42 tokens to every session, about $0.0002 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.