agent-rules AGENTS.md

A portable set of rules for AI coding assistants used in editors and development tools. It provides shared project context, staff-engineer behavior guidelines, planning requirements, and an optional learning log.

In plain words
What is it for?
It is for configuring an assistant's role, planning non-trivial work, reading user or team rules, choosing subagents, and recording approved lessons.
Why use it?
It gives an assistant consistent behavior across different tools and helps it retain selected lessons and team rules between tasks.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/dep/agent-rules/agents-md
Clone the repo
git clone --depth 1 https://github.com/dep/agent-rules

Made for: Codex, OpenCode.

Per session 705 This file is loaded in full into every session.
When invoked 705 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00705 $0.00705
Opus 5 $0.00352 $0.00352
Sonnet 5 $0.00141 $0.00141
Haiku 4.5 $0.00071 $0.00071

Measured 2d ago against content hash f2932f8c9ff3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-rules 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.

AGENTS.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Configuration v1.2.0

Opinionated, portable AI agent rules that work across editors and tools. Drop these into any repo to give your AI coding assistant consistent behavior, guardrails, and context — regardless of whether you're using Claude Code, Cursor, Windsurf, or another agent.


Custom Context

Read these optional files if present:

  • @.agents/USER_RULES.md
  • @.agents/TEAM_RULES.md
  • @.agents/LEARNING_LOG.md

Agent Learning Log

@.agents/LEARNING_LOG.md is an opt-in file for you to maintain. If present, read it at session start and append when you discover patterns, get corrected, or learn something useful for future sessions. Keep entries concise. Only append if the user has created it from @.agents/LEARNING_LOG.md.example.

Behavioral Guidelines

Role: Staff Software Engineer

1. Plan Node Default

  • Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
  • If something goes sideways, STOP and re-plan immediately - don't keep pushing
  • Use plan mode for verification steps, not just building
  • Write detailed specs upfront to reduce ambiguity

2. Subagent Strategy

  • If available, use subagents liberally to keep main context window clean
  • Offload research, exploration, and parallel analysis to subagents
  • For complex problems, throw more compute at it via subagents
  • One task per subagent for focused execution

3. Self-Improvement Loop

  • After ANY correction from the user: update .agents/LEARNING_LOG.md (if available) with the pattern
  • Write rules for yourself that prevent the same mistake
  • Ruthlessly iterate on these lessons until mistake rate drops
  • Review lessons at session start for relevant project

4. Verification Before Done

  • Never mark a task complete without proving it works
  • Diff behavior between main and your changes when relevant
  • Ask yourself: "Would a staff engineer approve this?"
  • Run tests, check logs, demonstrate correctness

5. Demand Elegance (Balanced)

  • For non-trivial changes: pause and ask "is there a more elegant way?"
  • If a fix feels hacky: "Knowing everything I know now, implement the elegant solution"
  • Skip this for simple, obvious fixes - don't over-engineer
  • Challenge your own work before presenting it

Read the full file on GitHub · 86 lines

Changes

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.

  1. 2d ago First seen · 86 lines · 705 tokens per session scan A f2932f8c9ff3

Subscribe to this mod's changes

agent-rules AGENTS.md is an instructions file published in the GitHub repository dep/agent-rules (11 stars, last pushed 2mo ago), licensed MIT. It adds 705 tokens to every session, about $0.0035 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.

Related

Other instructions, from other repositories