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/mcw-wellness/ai-dev-blueprint/agents-mdgit clone --depth 1 https://github.com/mcw-wellness/ai-dev-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/mcw-wellness/ai-dev-blueprint/agents-md)<a href="https://agentmods.dev/instructions/mcw-wellness/ai-dev-blueprint/agents-md"><img src="https://agentmods.dev/badge/instructions/mcw-wellness/ai-dev-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 | $0.00780 | $0.00780 |
| Opus 5 | $0.00390 | $0.00390 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
ai-dev-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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@soul.md @setup.md @preferences.md
Core principles
These apply to every task. If a suggestion violates one, call it out.
- KISS — simplest thing that works.
- YAGNI — only what's asked for.
- TDD — tests first, code second (experiments excepted).
- Spec-anchored — no code without a spec.
- Fail loud — never swallow an exception. A
catch/exceptthat logs and carries on hides the very failure it was meant to survive, and the system then lies about being healthy. Swallowing is undesired by default and requires my explicit approval, recorded in a comment naming the reason. Otherwise: let it propagate, or stop the affected work.
Status updates
Whenever you give me a duration or ETA (how long something will take, when it'll finish, when you'll wake up to check), include the current local time so I can compute the actual finish time. Run date to get it — don't guess from memory.
Format: ETA ~10 min (now 11:14, finishes ~11:24). Without the anchor, "10 min" is useless if I read the message late.
Playbooks
Hard gate — read the relevant playbook before you propose anything. Not just before coding. Proposing a title, directory structure, success criteria, or plan is acting. If you haven't read the playbook yet, your proposal is uninformed by the rules and will be wrong.
| Doing this | Read this |
|---|---|
| Starting a feature or fixing a bug | how-to-develop.md |
| Reviewing a plan (before coding) | how-to-review-spec.md |
| Reviewing code (after coding) | how-to-review-code.md |
| Writing tests | how-to-write-tests.md |
| Running or creating an experiment (incl. hardware) | how-to-run-experiments.md |
| Reverse-engineering legacy code | how-to-reverse-engineer.md |
| Validating parity with a legacy system | how-to-shadow-replay.md |
| Running a Ralph project (autonomous loop over multiple specs) | how-to-ralph-project.md |
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 · 49 lines · 780 tokens per session scan A ce5b3f495324
ai-dev-blueprint AGENTS.md is an instructions file published in the GitHub repository mcw-wellness/ai-dev-blueprint (2 stars, last pushed 2d ago), licensed MIT. It adds 780 tokens to every session, about $0.0039 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.