skill-git:commit

A version-control command for saving changes to coding-agent skills, where a skill is a set of instructions and supporting files.

In plain words
What is it for?
Use it to review skill changes, choose version updates and commit messages, then create Git commits and tags for the selected skills.
Why use it?
It shows what changed before committing, helping you avoid versioning the wrong files or missing unregistered skills.

Command

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/commit
Clone the repo
git clone --depth 1 https://github.com/KnowledgeXLab/skill-git
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,911 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.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.01911
Opus 5 $0.00025 $0.00955
Sonnet 5 $0.00010 $0.00382
Haiku 4.5 $0.00005 $0.00191

Measured 2d ago against content hash 1b67ee778375, 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:commit 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.

commands/commit.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running /skill-git:commit. Follow these steps exactly.

Task Tracking

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

  1. Scan for changes — warn about unregistered skills, then parallel-scan all skills for diffs
  2. Display change summary — show what changed and ask the user which skills to commit
  3. Suggest versions and messages — analyze diffs, propose semver bumps and commit messages
  4. Execute commits — run git add, commit, tag, and update config.json for confirmed skills

Prelude

!bash "${CLAUDE_PLUGIN_ROOT}/scripts/sg-prelude.sh" $ARGUMENTS

If STATUS is not ok:

  • Re-examine RAW_ARGUMENTS — check if the user expressed an agent name or intent that can be semantically resolved (e.g. a typo, a paraphrase, or an implicit default).
  • If you can determine intent, note the resolution (e.g. "Treating -a cluade as claude") and proceed.
  • If STATUS is not_initialized and INITIALIZED_AGENTS is non-empty, suggest the user run /skill-git:init -a <agent>, or mention which agents are already available.
  • If STATUS is error, display REASON as a plain-language error and stop.
  • If intent cannot be resolved, display a clear error and stop.

Use AGENT, GLOBAL_BASE, and SKILLS_JSON from prelude output for all subsequent steps. The skills map referred to throughout this document is the parsed content of SKILLS_JSON.

Agent name in positional position: If $ARGUMENTS contains a known agent name (claude, gemini, codex, openclaw) as a standalone positional token not preceded by -a, silently treat it as -a <agent>: override AGENT, re-read GLOBAL_BASE and SKILLS_JSON from ~/.skill-git/config.json for that agent. Do not pass it to any skill-name parsing steps.

Step 1a — Filesystem Scan

Run:

bash "${CLAUDE_PLUGIN_ROOT}/scripts/sg-warn-unregistered.sh" "<global_base>" '<skills_json>'

Display the output if any (do not stop, do not prompt).

Read the full file on GitHub · 184 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.

  1. 2d ago First seen · 184 lines · 50 tokens per session scan A 1b67ee778375

Subscribe to this mod's changes

skill-git:commit is a command published in the GitHub repository KnowledgeXLab/skill-git (41 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 1,911 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.