What is skill-git:init?

A setup command that begins version tracking for your skills by creating a separate Git repository in each skill folder and adding an initial version tag.

Use it once when setting up tracking for Claude, Gemini, Codex, or OpenClaw skills, optionally for a project.

It prepares skills for later versioning, comparison, rollback, and other skill-management commands.

skill-git:init — Command by KnowledgeXLab

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 commands/knowledgexlab/skill-git/init

Clone the repo

git clone --depth 1 https://github.com/KnowledgeXLab/skill-git

Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,374 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5	$0.00066	$0.01374
Opus 5	$0.00033	$0.00687
Sonnet 5	$0.00013	$0.00275
Haiku 4.5	$0.00007	$0.00137

Measured yesterday against content hash 3bf7cac5a958, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-git:init 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.

commands/init.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running /skill-git:init. Follow these steps in order. \

Task Tracking

You MUST create a task for each item below and update each task's status as you progress (pending → in_progress → completed):

Resolve agent — detect or prompt for the target agent (claude, gemini, codex, openclaw)
Explain what will happen — summarize the init steps to the user before executing
Verify git is installed — check git --version
Run initialization — execute sg-init.sh and display the full output

Step 1 — Resolve agent

Parse $ARGUMENTS for a -a <value> flag.

If -a was provided: use that value as agent. Validate it against the known agents:

value	base_dir
`claude`	`~/.claude`
`gemini`	`~/.gemini`
`codex`	`~/.codex`
`openclaw`	`~/.openclaw/skills`, `~/.openclaw/workspace/skills/`

If the value is not in the table, respond:

Unknown agent: "<value>"
Supported agents: claude, gemini, codex, openclaw

Then stop.

If -a was not provided: auto-detect using the following steps in order:

Step A — Check parent process: Run ps -p $PPID -o comm= and match the output:

contains claude → claude
contains gemini → gemini
contains codex → codex
contains openclaw or claw → openclaw

If matched, set agent and note: (agent auto-detected from process: <agent>)

Step B — Check user config (if Step A fails): Read ~/.skill-git/config.local.md and look for a default_agent field:

---
default_agent: gemini
---

If found, set agent from that value. Note: (agent from config: <agent>)

Step C — Prompt user (if Step B also fails):

Tell the user that the CLI tool could not be detected automatically, then use the AskUserQuestion tool:

question: "Which agent are you initializing skills for?"
header: "Agent"
options:
- label: "claude", description: "~/.claude/skills/"
- label: "gemini", description: "~/.gemini/skills/"
- label: "codex", description: "~/.codex/skills/"
- label: "openclaw", description: "~/.openclaw/skills/ + ~/.openclaw/workspace/skills/"
multiSelect: false

Read the full file on GitHub · 119 lines

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.

yesterday First seen · 119 lines · 0 tokens per session scan A 3bf7cac5a958

Subscribe to this mod's changes

skill-git:init is a command published in the GitHub repository KnowledgeXLab/skill-git (41 stars, last pushed 4mo ago), licensed MIT. It adds 66 tokens to every session and 1,374 once invoked, about $0.0003 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.

Git and workflow agent-skills claude-code claude-code-plugin

skill-git:init

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Task Tracking

Step 1 — Resolve agent

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement