skill-git:scan

A command that compares the rules and descriptions of registered coding-agent skills to find ones that overlap. It can suggest which skills may be combined.

In plain words
What is it for?
Use it to check all or selected skills for duplicated responsibilities before merging them. It saves a report of the results and shows possible merge suggestions.
Why use it?
It helps avoid maintaining several skills that cover the same work. It narrows comparisons to related skills instead of making you inspect every possible pair.

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/scan
Clone the repo
git clone --depth 1 https://github.com/KnowledgeXLab/skill-git
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,430 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 $0.00047 $0.06430
Opus 5 $0.00023 $0.03215
Sonnet 5 $0.00009 $0.01286
Haiku 4.5 $0.00005 $0.00643

Measured yesterday against content hash 70b6600c41a7, 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:scan 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/scan.md · 597 lines

How it starts

The opening of the file, as written. The whole thing — 597 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

All output shown to the user must be in English.

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. Resolve target skills — validate requested skills or use all registered skills
  2. Pre-filter by description — group skills by domain similarity, skip unrelated pairs
  3. Extract rules (Phase 1) — load from cache or dispatch subagents to extract rules per skill
  4. Cluster and analyze pairs (Phase 2) — pool rules into topics, derive overlap metrics per pair
  5. Save results and output report — persist to latest.json and display merge suggestions

Prelude

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

Parse $ARGUMENTS for remaining flags (after the prelude has consumed -a <value>):

  1. Scan for -f or --force. If present, set force = true; otherwise force = false.
  2. Extract all remaining tokens (non-flag, non-flag-value) as requested_skills list.

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 and proceed.
  • If STATUS is not_initialized and INITIALIZED_AGENTS is non-empty, suggest /skill-git:init -a <agent>.
  • 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 requested_skills.

Read the full file on GitHub · 597 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. yesterday First seen · 597 lines · 0 tokens per session scan A 70b6600c41a7

Subscribe to this mod's changes

skill-git:scan is a command published in the GitHub repository KnowledgeXLab/skill-git (41 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 6,430 once invoked, about $0.0002 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.