universal-agents AGENTS.md

universal-agents AGENTS.md is an instructions file for Codex, OpenCode from leochiu-a/universal-agents. It costs 610 tokens per session, scanned A, original, MIT.

A control manifest that explains how universal agents should discover and apply project skills and long-lived rules from an .agents directory.

In plain words
What is it for?
Following repository-specific skills, API or component rules, execution protocols, and response requirements when working in projects that use universal-agent instructions.
Why use it?
It tells an agent which instructions to load for a task and keeps response behavior consistent across environments that do not automatically load those files.

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/leochiu-a/universal-agents/agents-md
Clone the repo
git clone --depth 1 https://github.com/leochiu-a/universal-agents

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for universal-agents AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/leochiu-a/universal-agents/agents-md.svg)](https://agentmods.dev/instructions/leochiu-a/universal-agents/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/leochiu-a/universal-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/leochiu-a/universal-agents/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 610 This file is loaded in full into every session.
When invoked 610 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 $0.00610 $0.00610
Opus 5 $0.00305 $0.00305
Sonnet 5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured 4d ago against content hash a375ee9bdbce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

universal-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 4d 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 · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Universal Agents Control Manifest

All agents must emulate .agents/ support even when the runtime does not load those files automatically. Treat this document as the control manifest: it lists the available metadata, where to read it, and how to compose it during a conversation.

Reference layout:

.agents/
  skills/
    code-review/
      SKILL.md
  rules/
    api-guideline.md
    react-components-guideline.md
AGENTS.md

Execution protocol

  1. Always read this file before starting a task so you know which skills or rules to load from .agents/.
  2. Skills:
    • Load a skill only if its trigger condition matches the task. Example: code review tasks must load skills/code-review/SKILL.md.
    • Once loaded, obey the process and output format defined inside the skill file so the final response stays consistent.
  3. Rules:
    • Rules are long-lived constraints (API guidelines, React component practices, etc.). Whenever a task touches those domains, read the matching file under .agents/rules/.
    • Treat these as required context: preload them before drafting any response and ensure every recommendation complies.
  4. Response contract:
    • Explicitly mention which skills and rules are in effect.
    • Derive findings, recommendations, or code while enforcing all loaded constraints. If conflicts arise, ask for clarification before diverging.

Extending the manifest

  • Additional skills (architecture review, test planning, etc.) or rules (team code style, compliance requirements) can be added under the existing folders.
  • Keep AGENTS.md updated so future agents know when to load each artifact and how to combine them safely.

Rules vs. skills at a glance

Aspect Rules (Cursor-style) Skills (Claude-style)
Purpose Concise written instructions covering a domain. Full toolkits: guidance plus reusable templates and verified workflows.
Execution effort Agent interprets and implements from scratch. Drop-in code, docs, and checklists shorten build time.
Complexity focus Describes guardrails; depends on agent expertise. Encodes battle-tested patterns for tricky or specialized scenarios.
Maintenance Update the prose rule as policies evolve. Refresh the whole package (docs + sample code) when better solutions ship.

Read the full file on GitHub · 46 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. 4d ago First seen · 46 lines · 610 tokens per session scan A a375ee9bdbce

Subscribe to this mod's changes

universal-agents AGENTS.md is an instructions file published in the GitHub repository leochiu-a/universal-agents (59 stars, last pushed 9mo ago), licensed MIT. It adds 610 tokens to every session, about $0.0030 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

spec-kitty AGENTS.md

AGENTS.md instructions for Priivacy-ai/spec-kitty, covering spec kitty development guidelines, ⚠️ critical: load the project charter first, ⚠️ critical: template source location, ⚠️ critical: use canonical sources, never improvise and ⚠️ critical: git workflow — no direct pushes to origin/main.

Priivacy-ai/spec-kitty · 9,910 tokens

coral CLAUDE.md

Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).

cdknorow/coral · 1,898 tokens

gemini-cli-desktop AGENTS.md

Instructions for Piebald-AI/gemini-cli-desktop, a project described as: Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.

Piebald-AI/gemini-cli-desktop · 6 tokens

sessionview AGENTS.md

AGENTS.md instructions for tyql688/sessionview, covering sessionview, commands, app / frontend, gates must pass under both feature sets: default (gui) and and --no-default-features --features headless.

tyql688/sessionview · 2,157 tokens

SubFrame AGENTS.md

AGENTS.md instructions for Codename-11/SubFrame, covering subframe - subframe project, core working principle, relationship to native ai tools, session start and concurrent work & worktrees.

Codename-11/SubFrame · 3,973 tokens

codmate AGENTS.md

Instructions for loocor/codmate, a project described as: CodMate is a macOS SwiftUI app for managing CLI AI sessions: browse, search, organize, resume, and review work produced by Codex, Claude Code, and Gemini CLI. It focuses on speed, a compact three-column UI, and “ship it” workflows like Project Review (Git…

loocor/codmate · 5,081 tokens