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/leochiu-a/universal-agents/agents-mdgit clone --depth 1 https://github.com/leochiu-a/universal-agentsWrote 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/leochiu-a/universal-agents/agents-md)<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>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 | $0.00610 | $0.00610 |
| Opus 5 | $0.00305 | $0.00305 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
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.
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
- Always read this file before starting a task so you know which skills or rules to load from
.agents/. - 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.
- Load a skill only if its trigger condition matches the task. Example: code review tasks must load
- 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.
- Rules are long-lived constraints (API guidelines, React component practices, etc.). Whenever a task touches those domains, read the matching file under
- 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.mdupdated 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. |
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.
- 4d ago First seen · 46 lines · 610 tokens per session scan A a375ee9bdbce
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.
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.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
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.
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.
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.
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…