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/nimble-giant/ailloy/agents-mdgit clone --depth 1 https://github.com/nimble-giant/ailloyWrote 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/nimble-giant/ailloy/agents-md)<a href="https://agentmods.dev/instructions/nimble-giant/ailloy/agents-md"><img src="https://agentmods.dev/badge/instructions/nimble-giant/ailloy/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 | $0.01158 | $0.01158 |
| Opus 5 | $0.00579 | $0.00579 |
| Sonnet 5 | $0.00232 | $0.00232 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
ailloy 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ailloy — AI Agent Instructions
Ailloy is the package manager for AI instructions. This project uses Ailloy blanks for AI-assisted development workflows.
Behavioral Contract
@features.md
features.md is the terse, code-backed contract of ailloy's user-facing behaviors — read it before changing any feature so you don't regress existing behavior.
Standing rule: keep features.md current. Whenever you add a feature, or introduce or change a behavior or user expectation, update features.md in the SAME change. Every claim in it must be backed by the actual code. Treat it as part of the definition of done.
Available Commands
The following command blanks are available in the .claude/commands/ directory:
- brainstorm: Analyze an idea for feasibility, scope, and value using structured brainstorming techniques
- create-issue: Generate well-formatted GitHub issues with proper structure
- start-issue: Fetch GitHub issue details and begin implementation
- open-pr: Create pull requests with structured descriptions
- pr-description: Generate comprehensive PR descriptions
- pr-comments: Respond to PR review comments efficiently
- pr-review: Conduct comprehensive code reviews with silent/interactive modes
- preflight: Pre-flight checks and setup
- update-pr: Update existing pull requests
Available Skills
The following skills are available in the .claude/skills/ directory:
- brainstorm: Structured brainstorming methodology for evaluating ideas using freewriting, cubing, and journalistic techniques
- add-ailloy-blank: Guided workflow for creating new Ailloy blanks with proper mold structure
Workflow Blanks
The following workflow blanks are available in the official mold and can be installed into a project's .github/workflows/ via ailloy cast --with-workflows:
- claude-code: GitHub Actions workflow for the Claude Code agent (responds to @claude mentions in issues and PRs)
- claude-code-review: GitHub Actions workflow for automated PR reviews with Claude Code agent. Features brevity-focused formatting, collapsible sections, and comment management (updates summary, creates replies).
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 · 85 lines · 1,158 tokens per session scan A 782836dcc70c
ailloy AGENTS.md is an instructions file published in the GitHub repository nimble-giant/ailloy (10 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,158 tokens to every session, about $0.0058 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
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).