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/theam/facility/agents-mdgit clone --depth 1 https://github.com/theam/facilityWhat 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 | $0.00717 | $0.00717 |
| Opus 5 | $0.00358 | $0.00358 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
facility 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering instructions
Critical-change regression coverage
Changes to security- or money-critical surfaces—including authentication, authorization/RBAC, tenant scoping, secrets and cryptography, billing or budget enforcement, webhook signature validation, and privileged external integrations—are incomplete without both unit tests and integration tests.
Integration tests must use deterministic fakes or local servers for external systems. The default CI suite must not need live credentials or network access. Cover successful operation and relevant denial paths, including malformed, expired, revoked, replayed, and cross-tenant inputs. Add a regression test that would fail if the previous unsafe behavior returned.
Commit subjects set the released version
Write every commit subject as a Conventional Commit:
<type>[(scope)][!]: <what changed>
Use one of these types: feat, fix, perf, docs, style, refactor,
test, build, ci, chore, or revert.
This is not a style preference. Release-on-merge derives the next version from the subjects merged since the last release. Subject validation lands before that workflow so the history it will consume is already trustworthy: a subject that lies about the kind of change ships the wrong version number to everyone who installed the package.
| Subject | What it releases while the version is 0.x |
|---|---|
fix: …, perf: …, revert: … |
a patch |
feat: … |
a patch |
<type>!: …, or a BREAKING CHANGE: footer |
a minor |
docs: …, test: …, refactor: …, ci: …, chore: …, build: …, style: … |
nothing on its own |
Two consequences worth internalising:
- A user-visible change hidden behind
chore:never reaches users. It sits onmainunreleased until something else triggers a release, and then ships unannounced in someone else's release notes. - A breaking change without
!ships as a patch. Mark it, in the subject or in aBREAKING CHANGE:footer, and say in the body what a user has to change.
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 · 56 lines · 717 tokens per session scan A f479c90dee07
facility AGENTS.md is an instructions file published in the GitHub repository theam/facility (43 stars, last pushed 4d ago), licensed Apache-2.0. It adds 717 tokens to every session, about $0.0036 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
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.
buildNext
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).
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.
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).
spec-kit 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
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.