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/x0c/agent-friendly-cli-skill/agents-mdgit clone --depth 1 https://github.com/x0c/agent-friendly-cli-skillWhat 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 | $0.00406 | $0.00406 |
| Opus 5 | $0.00203 | $0.00203 |
| Sonnet 5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
agent-friendly-cli-skill 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.
What it actually says
AGENTS.md
本仓库是 agent-friendly-cli skill 的源码与发布仓。在本仓库工作时遵守以下约定。
仓库结构
- 仓库根即 skill 本体（
SKILL.md+references/+agents/openai.yaml）。本地开发权威源在~/.config/agentsync/skills/agent-friendly-cli/，改动先落权威源，再同步到本仓库——不要只改本仓库副本。
硬约束
- 发布前必须先 clone 远端、
diff -rq比对：远端可能有其他机器推的更新（含仅改远端的修复，如 README 安装 URL），先合并回本地权威源再同步推送，禁止直接 rsync 覆盖。 - commit 身份双字段均为 x0c（
GIT_COMMITTER_NAME/GIT_COMMITTER_EMAIL+--author，[email protected]），真实姓名邮箱不进提交历史。 - 不推送内网专属内容：公司内部平台的类名、路径、配置不得写入本仓库；示例用通用表述（不写具体公司/平台名）。
- 代码注释、文档默认中文。
文档导航
README.md：仓库门面，对外介绍 skill 的适用场景与安装方式；仓库改名或安装方式变化时同步更新其中的 clone URL。SKILL.md：方法论入口（P0 硬性要求、工作流、契约演进纪律），详细原则按需读 references。references/pitfalls.md：踩坑清单；references/design-principles.md：设计原则；references/verification.md：验收清单。
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.
- 2d ago First seen · 21 lines · 406 tokens per session scan A 9260db22e4bb
agent-friendly-cli-skill AGENTS.md is an instructions file published in the GitHub repository x0c/agent-friendly-cli-skill (1 stars, last pushed 9d ago), licensed MIT. It adds 406 tokens to every session, about $0.0020 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.
Other instructions, from other repositories
AgentPipe AGENTS.md
Instructions for dwebagents/AgentPipe: You are a 100x developer. Your task is to improve this repository. Begin every issue and PR comment with "Yes chef. Right away chef.".
Agent-HTML AGENTS.md
Instructions for Sayhi-bzb/Agent-HTML, covering gitnexus, docs writing rules, content routes, canvas constitution and archive rule.
KumoApp AGENTS.md
AGENTS.md instructions for ProjectKumo/KumoApp, covering kumo agent guidelines, development documentation, documentation maintenance, ui copy constraints and swiftui native component constraints.
cf-saas-starter-react-router AGENTS.md
AGENTS.md instructions for SeanningTatum/cf-saas-starter-react-router, covering agents.md — brain pointer, brain-axi cli — the harness interface, read-before-task workflow, slash commands (deterministic gates) and harness — what holds this together.
AgentPipe CLAUDE.md
Instructions for dwebagents/AgentPipe, a project described as: High performance multithreaded task execution and optimization engine for agents and dweb apps.
Agent-HTML CLAUDE.md
Instructions for Sayhi-bzb/Agent-HTML, a project described as: You don't need a chat ui but a canvas with ai.