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.
git clone --depth 1 https://github.com/huuanh20/awesome-ai-agent-skillsWrote 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/commands/huuanh20/awesome-ai-agent-skills/init)<a href="https://agentmods.dev/commands/huuanh20/awesome-ai-agent-skills/init"><img src="https://agentmods.dev/badge/commands/huuanh20/awesome-ai-agent-skills/init/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/huuanh20/awesome-ai-agent-skills/init"><img src="https://agentmods.dev/badge/commands/huuanh20/awesome-ai-agent-skills/init.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00044 | $0.03580 |
| Opus 5 | $0.00022 | $0.01790 |
| Sonnet 5 | $0.00009 | $0.00716 |
| Haiku 4.5 | $0.00004 | $0.00358 |
Grade B, and why
init scanned grade B with 1 finding 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Write assembled JSON (no comments) to `<target>/.claude/settings.json`. How it starts
The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ck:init — Bootstrap a Project or Reconfigure
Usage
/ck:init [target-path] # full bootstrap wizard for a target project
/ck:init --show # print current project's .ck.json
/ck:init --reset # wipe current project's .ck.json
How to execute this command
Read $ARGUMENTS. Dispatch on the first token:
--show→ run Show mode below--reset→ run Reset mode below- anything else (or empty) → treat as optional target path, run Wizard mode
Wizard mode uses AskUserQuestion select boxes for all choices. Whenever the user selects Abort: output Aborted. No files written. and stop immediately.
The source directory is always $CLAUDE_PROJECT_DIR/.claude/ (this repo).
Show mode
Read .ck.json at the current project root. Print a formatted summary of all fields. If the file does not exist, say so and suggest running /ck:init.
Reset mode
Delete .ck.json at the current project root if it exists. Confirm: Config reset. Run /ck:init to reconfigure.
Wizard mode
Step 0 — Target path + preflight
If no path in $ARGUMENTS, ask with plain text:
Target project path (absolute or relative to current dir):
Resolve to absolute path. Validate:
- Does not exist →
AskUserQuestion: "Path does not exist. Create it?" /Create it/Abort - Exists but not a directory → abort with error.
Once the path is validated, run both checks and present any triggered ones in a single AskUserQuestion with 2 questions (omit a question if its condition is false):
Q: Python — only if Python 3 is not found in PATH:
"⚠ Python 3 not found. Hooks require Python 3.x. Continue anyway?"
Options: Continue anyway / Abort
Q: Conflict — only if <target>/.claude/ already exists:
".claude/ already exists in that project. How should we proceed?"
Options: Merge (copy only missing files — Recommended) / Overwrite / Abort
Use the conflict answer directly in Step 5 execution — Merge skips existing files, Overwrite replaces all.
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.
- 8d ago First seen · 378 lines · 0 tokens per session scan B 865a5efaaa93
init is a command published in the GitHub repository huuanh20/awesome-ai-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 3,580 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
prompts
Search and discover AI prompts from prompts.chat.
diagrams
Analyze the provided code, architecture, or concept and generate a clear, well-structured Mermaid diagram that visualizes the relationships, flow, or structure.
code-review
Perform a thorough code review that verifies functionality, maintainability, and security before approving a change. Focus on architecture, readability, performance implications, and provide actionable suggestions for improvement.
git-commit
Create a git commit for the current changes using Conventional Commits-style format.
security-audit
Command "security-audit" from adriannoes/awesome-agentic-ai, covering security audit, steps and security checklist.