agentmods.dev

agent-kit AGENTS.md

Repository instructions for agent-kit, a public software repository whose tracked files can be seen online.

In plain words
What is it for?
Use them when changing agent-kit, reviewing skills or vendor updates, and running its required tests and checks.
Why use it?
They help prevent credentials, private notes, unsafe updates, and licensing mistakes from entering the project.

Instructions file for CodexOpenCode

2 27d ago A scan 185 tokens original MIT
View the source file cubxxw/agent-kit
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/cubxxw/agent-kit/agents-md
Clone the repo
git clone --depth 1 https://github.com/cubxxw/agent-kit

Made for: Codex, OpenCode.

Per session 185 This file is loaded in full into every session.
When invoked 185 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 $0.00185 $0.00185
Opus 5 $0.00093 $0.00093
Sonnet 5 $0.00037 $0.00037
Haiku 4.5 $0.00018 $0.00018

Measured 2d ago against content hash bb2dd73183c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-kit 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 · 19 lines

What it actually says

Agent Kit repository instructions

This is a public repository. Treat every tracked byte as internet-visible.

  • Never copy credentials, authentication state, transcripts, memories, private notes, or machine-local overrides into this repository.
  • Use environment-variable names in examples; never include real values.
  • Keep catalog.json as the source of truth for accepted skills and upstream pins.
  • Treat docs/top-skills.md as a discovery radar, not an installation list. Add only a named skill that passes the full curation gate.
  • Preserve third-party license files and attribution.
  • Do not overwrite an existing user skill directory. The installer must fail safely on conflicts.
  • Run python3 -m unittest discover -s tests -v and ./bin/agent-kit doctor --strict after changes.
  • Review executable vendor changes manually before accepting an upstream update.
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 · 19 lines · 185 tokens per session scan A bb2dd73183c5

Subscribe to this mod's changes

agent-kit AGENTS.md is an instructions file published in the GitHub repository cubxxw/agent-kit (2 stars, last pushed 27d ago), licensed MIT. It adds 185 tokens to every session, about $0.0009 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.

ProductivityTestingagent-skillsai-agentsautomationcc-switchclaude-codecodex
Related

Other instructions, from other repositories

LoongPort CLAUDE.md

Instructions for SailingLoong/LoongPort, covering loongport 代码仓规则, 设计档案在另一个仓, 一、最高优先级：能复用 cc-switch 的就复用, 判定顺序（自上而下，命中即停） and 改上游文件时：改动面越小越好.

SailingLoong/LoongPort · 8,033 tokens

Tresor CLAUDE.md

Instructions for Ladbaby/Tresor, covering claude.md, project overview, configuration, config file locations (auto-detected in order) and yaml structure.

Ladbaby/Tresor · 3,686 tokens

n2-fieldops CLAUDE.md

Instructions for download4you/n2-fieldops, covering n2-fieldops contributor profile, runtime surfaces, required checks, editing rules and scope and safety.

download4you/n2-fieldops · 632 tokens

n2-fieldops AGENTS.md

Instructions for download4you/n2-fieldops, covering prompt decorators (runtime awareness), language, scope and cooperation, network context and personality.

download4you/n2-fieldops · 4,520 tokens

agent-context-bridge AGENTS.md

Instructions for Yongthyuan/agent-context-bridge, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

Yongthyuan/agent-context-bridge · 649 tokens

codex-provider-hub AGENTS.md

AGENTS.md instructions for AI-Routing-Research-Institute/codex-provider-hub, covering 项目级 ai 强制约束, 唯一交付入口, 开发前门禁, 开发与说明同步 and git 与 pr.

AI-Routing-Research-Institute/codex-provider-hub · 998 tokens