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/efailution/aicac/agents-mdgit clone --depth 1 https://github.com/eFAILution/AICaCWhat 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 | $0.00824 | $0.00824 |
| Opus 5 | $0.00412 | $0.00412 |
| Sonnet 5 | $0.00165 | $0.00165 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
AICaC 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Assistant Instructions (AICaC repo)
This repository specifies and tools the AI Context as Code (AICaC) v2.0
convention. It dogfoods itself: .ai/ holds structured YAML validated against
spec/v2/ JSON Schemas.
Router — load ONLY the relevant file
Each .ai/*.yaml has a top-level summary: field. Read summary first to
confirm you've picked the right file before loading the rest. The optional
.ai/index.yaml advertises available keys per file without loading content.
| Query intent | Load this file only |
|---|---|
| Project overview, entrypoints, dev/test commands | .ai/context.yaml |
| Components, dependencies, data flow | .ai/architecture.yaml |
| How to do X, adoption steps, migration, measurement | .ai/workflows.yaml |
| Why we did X, trade-offs, ADRs | .ai/decisions.yaml |
| Errors, validation failures, troubleshooting | .ai/errors.yaml |
| Which ids/keys exist in each file | .ai/index.yaml |
Examples:
- "How do I run the measurements?" →
.ai/workflows.yaml→run_token_measurement - "Why is v2.0 dict-keyed?" →
.ai/decisions.yaml→ADR-008 - "What does v1.x list form look like?" →
.ai/errors.yaml→DEPRECATED_V1_LIST_FORM - "What commands can I run?" →
.ai/context.yaml→common_tasks
Working on this repo
- Canonical spec lives in
spec/v2/. Every.ai/*.yamlmust validate. Run:python3 .github/actions/aicac-adoption/scripts/validate.py . - Changes to schemas must include: schema update, whitepaper update, and
at least one example file update (this repo's
.ai/and/orvalidation/examples/sample-project/.ai/). - Cross-references (
touches_components,affects_components,depends_on,superseded_by) are validator-enforced. Don't add a workflow referencingapiifapiisn't a component. - Token measurements:
make measure-all. Results go toexperiments/results.json. Checked-in reference:validation/examples/results/. - Tests:
cd .github/actions/aicac-adoption && pytest - Claude Code skill:
.claude/skills/aicac/SKILL.md— the on-ramp for Claude Code users to route, bootstrap, validate, and keep.ai/in sync.
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 · 63 lines · 824 tokens per session scan A 731baa6cb6e5
AICaC AGENTS.md is an instructions file published in the GitHub repository eFAILution/AICaC (5 stars, last pushed 1mo ago), licensed MIT. It adds 824 tokens to every session, about $0.0041 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.
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.