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/slopus/happy-agent/agents-mdgit clone --depth 1 https://github.com/slopus/happy-agentWhat 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 | $0.06426 | $0.06426 |
| Opus 5 | $0.03213 | $0.03213 |
| Sonnet 5 | $0.01285 | $0.01285 |
| Haiku 4.5 | $0.00643 | $0.00643 |
Grade A, and why
happy-agent 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.
How it starts
The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Master plans
Read master-plans/00-master-plan.md first, before any other work. It explains how master plans are used and maintained. Then find every plan in master-plans/ relevant to your task and read each one in full before starting.
Master plans are dictated by the user and describe where the product is going, in what order, and what counts as done. They outrank conclusions drawn from the existing code. Do not create, edit, rename, or delete a file in master-plans/ unless the user explicitly asks for that change in the current task. When the code contradicts a master plan, report the contradiction instead of revising the plan.
All persistent plans must live in master-plans/ and follow the master-plan rules above. Do not create design documents, implementation plans, slash-command plan artifacts, or planning directories anywhere else in the repository, including docs/plans/.
Discussion notes that support or contextualize master plans must live only in
master-plans/notes/. Do not create these notes in the master-plans/ root,
in another documentation directory, or anywhere else in the repository.
API specification
Do not create, edit, rename, or delete any API.md file without direct human
input in the current task that explicitly authorizes the specific API
specification change.
packages/happy-agent/API.md is the authoritative Happy Agent API contract. Client types,
runtime schemas, daemon behavior, tests, and documentation must conform to it exactly. Never
invent, implement, preserve, or release behavior that deviates from the specification; stop and
request a human-directed specification change when the desired behavior is not already described.
Happy Agent API compatibility begins with protocol version 22. From version 22 onward, every API change must be backward-compatible and additive: never remove or rename an existing field, and never add a required field. New fields must be optional so older clients and daemons can ignore them safely. If a desired change cannot be made within those constraints, stop and request direct human guidance rather than breaking compatibility.
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 · 332 lines · 6,426 tokens per session scan A 4a2f1e34975f
happy-agent AGENTS.md is an instructions file published in the GitHub repository slopus/happy-agent (22 stars, last pushed 4d ago), licensed MIT. It adds 6,426 tokens to every session, about $0.0321 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
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.