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/owainlewis/blueprint/agents-mdgit clone --depth 1 https://github.com/owainlewis/blueprintWrote 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.
[](https://agentmods.dev/instructions/owainlewis/blueprint/agents-md)<a href="https://agentmods.dev/instructions/owainlewis/blueprint/agents-md"><img src="https://agentmods.dev/badge/instructions/owainlewis/blueprint/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01172 | $0.01172 |
| Opus 5 | $0.00586 | $0.00586 |
| Sonnet 5 | $0.00234 | $0.00234 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
blueprint 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blueprint repository policy
Blueprint is a small set of instructions for AI coding. It separates deciding what to build from shipping code.
Principles
- Give agents outcomes, constraints, and proof. Trust them with mechanics.
- Keep one skill per meaningful engineering phase or delivery outcome.
- Keep current architecture separate from proposed design.
- Review technical proposals before implementation when a wrong choice could materially affect behavior, data, security, scale, performance, compatibility, operations, cost, or proof.
- Update an existing architecture document when code changes ownership, dependency direction, protocols, stored data, trust boundaries, deployment topology, or hard limits.
- Skip phases that add no value. Small, decided work can go straight to implementation.
- A task is ready when a new agent can finish it without asking product or technical questions.
- Each pull request delivers one focused outcome and its proof. A reviewer should not have to separate unrelated work to understand it.
- Separate refactoring when it would hide the behavior change. Small local cleanup may stay when it makes that change easier to review.
- Logic changes include automated tests for changed behavior and affected failure paths, including any named in the acceptance criteria.
- Refactors include tests for behavior that must not change.
- If automated tests cannot exercise the affected behavior, explain why and give other evidence.
- Review checks correctness. Ask for a simpler design when it can deliver the same outcome and proof with less state, indirection, duplication, or operational work.
- Do not block on personal taste. Cite technical evidence or repository conventions.
- Browser behavior is proven in a real browser, not by reading source.
- If the task, design, or plan is wrong, update it before changing more code.
- Prefer the smallest complete change. Do not mix product work with unrelated cleanup.
- Humans review decisions and normally merge. Agents may merge only when the user explicitly delegates it. Explicitly naming
/codex-issue-coordinatordelegates merge authority for the supplied batch after its quality gates pass; an implicit skill match does not.
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.
- 4d ago First seen · 73 lines · 1,172 tokens per session scan A 836060c5245a
blueprint AGENTS.md is an instructions file published in the GitHub repository owainlewis/blueprint (375 stars, last pushed 5d ago), licensed MIT. It adds 1,172 tokens to every session, about $0.0059 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
spec-superflow GEMINI.md
Gemini CLI instructions for MageByte-Zero/spec-superflow, covering spec-superflow and spec-superflow v1.2.0 | 阶段: {{state}} | 工作流: {{workflow}}.
spec-superflow copilot-instructions.md
Copilot instructions for MageByte-Zero/spec-superflow, covering phase guard, ✅ 允许操作, ⛔ 禁止操作 and 🔔 决策点.
spec_driven_develop CLAUDE.md
Instructions for zhu1090093659/spec_driven_develop: Read AGENTS.md first. It is the shared project-level instruction source for Codex, OpenCode, Cursor, Claude Code, and other Markdown-aware coding agents.
racecraft-plugins-public AGENTS.md
Instructions for racecraft-lab/racecraft-plugins-public, covering repository agent instructions, working rules, 1. surface assumptions before editing, 2. make the simplest change that solves the task and 3. keep edits surgical.
speq-skill CLAUDE.md
Instructions for marconae/speq-skill, covering local development rules, rules and commands.
aiops copilot-instructions.md
Instructions for yugasun/aiops, covering copilot instructions, >, lean, ladder and rules.