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/jastice/rules_agents/agents-mdgit clone --depth 1 https://github.com/jastice/rules_agentsWhat 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 | $0.01959 | $0.01959 |
| Opus 5 | $0.00979 | $0.00979 |
| Sonnet 5 | $0.00392 | $0.00392 |
| Haiku 4.5 | $0.00196 | $0.00196 |
Grade A, and why
rules_agents 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This file applies to the entire repository.
What This Repo Is
rules_agents is a Bazel-based repo-scoped agent environment tool.
Current implemented scope:
- supported agent clients:
codex,claude_code,pi - local skills declared in Bazel with
agent_skill(...) - remote skills synthesized from git archive downloads with
skill_deps.remote(...) - profile artifacts declared with
agent_profile(...) - concrete runners declared with
agent_runner(...) - repo-local installation into native agent directories
- validation and launch flows through
doctor,manifest,setup, andrun
Non-goals:
- general agent orchestration
- global user config management
- agent binary installation
- secret storage or secret minting
Source Of Truth
- Treat current code, tests, and repository docs as the source of truth.
- Treat everything under
spec/as historical reference unless the user explicitly says to adopt or follow a spec document. - If a task explicitly references a spec doc, use only the relevant sections and say that the spec is being treated as design input for that task.
Current Public Surface
The public Bazel API today is:
agent_skillagent_profileagent_runnerskill_deps
Current behavior:
agent_skill(...)packages one portable skill bundle rooted atSKILL.mdagent_profile(...)builds a reusable profile artifact and:name_manifestagent_runner(...)realizes a profile for one client and generates:name,:name_setup,:name_run,:name_doctor, and:name_manifestskill_deps.remote(...)synthesizes remoteagent_skilltargets from archive contentsskill_deps.registries(...)enables registry discovery, not installation by itself
Do not describe this repo as only exposing agent_skill, agent_profile, and skill_deps. agent_runner is part of the implemented public surface.
Core Constraints
Keep the implementation narrow and boring:
- install Codex skills under
.agents/skills - install Claude Code skills under
.claude/skills - install Pi skills under
.pi/skills - support Linux and macOS; do not claim Windows support unless the code, docs, and tests are updated together
- rely on normal repository-root discovery for both clients
- do not depend on
CODEX_HOMEfor Codex skill installation - do not synthesize a global Claude home
- keep generated file ownership limited to tool-managed subdirectories
- preserve machine-readable manifest and doctor outputs
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 · 197 lines · 1,959 tokens per session scan A 72034ce0cdc6
rules_agents AGENTS.md is an instructions file published in the GitHub repository jastice/rules_agents (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,959 tokens to every session, about $0.0098 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
mini-swe-agent copilot-instructions.md
Copilot instructions for SWE-agent/mini-swe-agent, covering style guide, test style, bad and good.
Octop AGENTS.md
Instructions for TencentCloud/Octop, covering agents.md, 1. collaboration principles, think before writing, simplicity first and surgical edits.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
relay AGENTS.md
Instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.
hands-on-modern-rl AGENTS.md
AGENTS.md instructions for walkinglabs/hands-on-modern-rl, covering repository guidelines, project structure, commands, editing rules and tikz → svg workflow.
neeko AGENTS.md
Instructions for tincopper/neeko, covering neeko — repository guidelines, 项目概览, 目录结构, 前端（feature-based 架构） and 后端（domain-driven 模块化架构）.