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/bgrgicak/roomy/agents-mdgit clone --depth 1 https://github.com/bgrgicak/RoomyWrote 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/bgrgicak/roomy/agents-md)<a href="https://agentmods.dev/instructions/bgrgicak/roomy/agents-md"><img src="https://agentmods.dev/badge/instructions/bgrgicak/roomy/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 | $0.00557 | $0.00557 |
| Opus 5 | $0.00279 | $0.00279 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
Roomy 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 5d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ensure quality
We are building a prototype, it's crucial for us to move fast and make the right architectural decisions, but features should now be simplified and isolated as much as possible so that refactoring and iteration are easy and low-risk.
Automated testing
- Implement integration tests before working on a feature.
- Run relevant tests after implementing a feature to ensure it works as expected.
- Tests must be real where it matters: real Postgres, real Docker, real WebSocket transport, real on-disk storage. No fakes as the only coverage of those surfaces.
- AI model calls are the exception. The free
opencode/big-pickletier we used to lean on is gone. New policy:- Most server tests don't need a real model — inject a no-op
execRunFnviacreateRunManager({ pool, execRunFn: async () => ({ exitCode: 0 }) })and assert on routes, DB, ownership, status decoration, etc. - For tests that do need actual agent output, use the aimock helper at packages/server/api/test/helpers/aimock.ts — it boots a local HTTP server that speaks the Anthropic Messages and OpenAI Chat Completions surfaces, runs on a random port, and returns deterministic canned responses (or replays a recorded fixture). Point pi at it via
ANTHROPIC_BASE_URL/OPENAI_BASE_URL(the sandbox env, not just the test runner's). Record fixtures once against a real key on a developer machine; replay forever in CI. - Real-API smoke tests are allowed but must be opt-in (skip when no
ANTHROPIC_API_KEY/OPENAI_API_KEYin env) so CI is free and deterministic.
- Most server tests don't need a real model — inject a no-op
- For substantial feature work or cross-package changes, run
npm run ci:localbefore calling the work complete, or explicitly report why it could not be run. This requires Node 23 and Docker. - Prefer targeted tests while iterating, then use the full local CI mirror as the final verification for non-trivial changes.
Code review
After you are done with a feature, run /review-pr and address the feedback provided by the reviewer. Don't just accept the feedback, scrutinize it and address the root cause of the issue if there is one.
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.
- 5d ago First seen · 35 lines · 557 tokens per session scan A b980dadc1758
Roomy AGENTS.md is an instructions file published in the GitHub repository bgrgicak/Roomy (11 stars, last pushed 2mo ago), licensed MIT. It adds 557 tokens to every session, about $0.0028 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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 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.
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).