agentmods.dev

atoi-plugins AGENTS.md

Repository instructions for the Atoi plugin companion, which distributes Atoi integrations for coding-agent tools. They describe which files are authoritative, how generated files are produced, and how changes are checked.

In plain words
What is it for?
Use them when developing, generating, verifying, or preparing changes to the Atoi plugin companion.
Why use it?
They prevent edits to generated files and clarify the required checks and security boundaries for maintaining the repository.

Instructions file for CodexOpenCode

0 16d ago A scan 344 tokens original MIT
View the source file creative-int/atoi-plugins
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/creative-int/atoi-plugins/agents-md
Clone the repo
git clone --depth 1 https://github.com/creative-int/atoi-plugins

Made for: Codex, OpenCode.

Per session 344 This file is loaded in full into every session.
When invoked 344 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 $0.00344 $0.00344
Opus 5 $0.00172 $0.00172
Sonnet 5 $0.00069 $0.00069
Haiku 4.5 $0.00034 $0.00034

Measured yesterday against content hash 70de70a1d528, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

atoi-plugins 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 yesterday.

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 · 50 lines

What it actually says

Atoi Plugins

This repository is Atoi's public agent-plugin-companion. It distributes portable skills and generated Claude Code, Codex, Cursor, MCP, and registry metadata. The Atoi product repo remains the runtime and schema authority.

Source of truth

atoi.config.ts is the single hand-edited source for product identity, companion metadata, MCP endpoint and authentication posture, supported clients, and distributed skills.

Never hand-edit generated files:

  • .mcp.json
  • server.json
  • .claude-plugin/
  • .codex-plugin/
  • .cursor-plugin/
  • the README install block between generated markers

Platform posture

Tooling-only companion repo; no product runtime surface.

Delivery loop

pnpm generate
pnpm smoke
git status --short
git add <intentional-files>
git commit -m "feat: ..."

Run pnpm verify before every commit. Publishing and pushing are owner actions unless a task explicitly authorizes them.

Boundaries

  • The client boundary is atoi mcp serve; never put an operator token in a manifest, example, log, receipt, or skill.
  • Skills may use the public Atoi CLI and documented MCP tools. They must not depend on private paths or another product repository.
  • Do not add workspace, Turbo, Biome, Knip, Codecov, TESTING.md, or .npmrc machinery while this remains an agent-plugin-companion.
  • Do not publish npm packages or MCP Registry entries from this repository.

CLAUDE.md must remain a symlink to this file.

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. yesterday First seen · 50 lines · 344 tokens per session scan A 70de70a1d528

Subscribe to this mod's changes

atoi-plugins AGENTS.md is an instructions file published in the GitHub repository creative-int/atoi-plugins (0 stars, last pushed 16d ago), licensed MIT. It adds 344 tokens to every session, about $0.0017 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.

abbieagent-skillsclaude-codecodexcursordeveloper-tools
Related

Other instructions, from other repositories

awesome-copilot-id AGENTS.md

Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.

GulajavaMinistudio/awesome-copilot-id · 7,686 tokens

hiveshare CLAUDE.md

Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.

KB-perByte/hiveshare · 1,301 tokens

llm-safe-haven CLAUDE.md

Instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.

pleasedodisturb/llm-safe-haven · 1,322 tokens

kleosrules AGENTS.md

Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).

kleosr/kleosrules · 417 tokens

coding-agent-safety-gate AGENTS.md

Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.

ASER-ho/coding-agent-safety-gate · 589 tokens

yapcap CLAUDE.md

Claude Code instructions for TopiCsarno/yapcap, a project described as: Native COSMIC panel applet showing local usage limits for Codex, Claude Code, and Cursor.

TopiCsarno/yapcap · 3 tokens