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/borda/ai-rig/agents-mdgit clone --depth 1 https://github.com/Borda/AI-RigWrote 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/borda/ai-rig/agents-md)<a href="https://agentmods.dev/instructions/borda/ai-rig/agents-md"><img src="https://agentmods.dev/badge/instructions/borda/ai-rig/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 | $0.02049 | $0.02049 |
| Opus 5 | $0.01025 | $0.01025 |
| Sonnet 5 | $0.00410 | $0.00410 |
| Haiku 4.5 | $0.00205 | $0.00205 |
Grade A, and why
AI-Rig 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 today.
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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Agent Instructions
- Any policy change in one listed instruction file must trigger a relevance review of every other listed file before completion.
- Synchronize applicable shared policy in either direction; preserve intentional agent-specific differences and record when no counterpart change is needed.
Instruction Layering
- Repository-wide policy belongs in this top-level file.
- Lower-scope instruction files inherit it and must add only narrower rules or explicit exceptions, never repeat the same policy; when a top-level policy changes, review lower layers for conflicts or obsolete duplication rather than copying the new text into them.
Edit Scope
- All edits stay inside this project directory. Never edit
$CODEX_HOMEor~/.claude/directly — both are install targets populated from this checkout, and a hand-edit there is overwritten on the next sync. - Permitted roots:
.codex/(Codex config, skills, session policy),.claude/settings.jsonand.claude/settings.local.json,plugins/*/{agents,skills,rules,hooks,bin}/. - The Makefile installs from the pushed GitHub remote, not the local working tree: commit and push first, then
make sync-claudeormake sync-codex. Running it against uncommitted work silently installs the previous state. - Never initiate propagation mid-task; it is a deliberate human-triggered step.
Core Principles
Simplicity and reliability come first. Understand the affected flow and root cause, then prefer the smallest clear, reversible solution that satisfies the verified contract. Prefer established project patterns, standard tools, and deletion over new abstractions, dependencies, configuration, or layers; add complexity only when current evidence proves it necessary.
Verification is part of implementation. Work is not complete until relevant checks pass and failures, residual risks, and deliberately deferred scope are reported accurately.
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.
- today Changed · +4 lines · +48 tokens per session 61be0a654a49
- 3d ago First seen · 97 lines · 2,001 tokens per session scan A 2c06b636a4b8
AI-Rig AGENTS.md is an instructions file published in the GitHub repository Borda/AI-Rig (25 stars, last pushed today), licensed Apache-2.0. It adds 2,049 tokens to every session, about $0.0102 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
plinth CLAUDE.md
Claude Code instructions for jabrena/plinth, a project described as: Plinth is an AI-native engineering toolkit for modern Java enterprise SDLC, built around reusable Commands, Agents, Skills, and MCP Servers.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
invokta CLAUDE.md
Instructions for vinilana/invokta, a project described as: A TypeScript framework for reusable domain AI capabilities across direct, CLI, and MCP transports.
github-copilot-instructions pytest.instructions.md
Comprehensive instructions for using pytest and pytest-cov for Python testing and coverage.
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).