skill-git:check

A command that checks a coding skill and its agent configuration for conflicting rules, project or global configuration problems, and security issues.

In plain words
What is it for?
Use it to inspect a skill, read its related configuration, run consistency and security checks, and optionally guide fixes.
Why use it?
It helps find problems before a skill is used or changed, including mismatched instructions and unsafe settings.

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/check
Clone the repo
git clone --depth 1 https://github.com/KnowledgeXLab/skill-git
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,343 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 $0.00039 $0.04343
Opus 5 $0.00019 $0.02171
Sonnet 5 $0.00008 $0.00869
Haiku 4.5 $0.00004 $0.00434

Measured yesterday against content hash 62ff421fa441, 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:check 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/check.md · 454 lines

How it starts

The opening of the file, as written. The whole thing — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are executing /skill-git:check. Follow the steps below precisely.

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. Parse arguments and resolve skill — extract skill name, find the file across all known paths
  2. Resolve agent configuration — determine agent and locate config files
  3. Read skill and config files — load SKILL.md and agent config files
  4. Extract and cache rules — run rule extraction (or load from cache) for skill and configs
  5. Run checks — internal consistency, project config conflicts, global config conflicts, security scan
  6. Output report — format and display the full check report
  7. Interactive resolution — work through each fixable conflict if the user chooses to fix (conditional)
  8. Confirm and write changes — display pending change summary, wait for confirmation, apply file edits to skill and config files (conditional)

Prelude

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

If STATUS is ok: use AGENT and GLOBAL_BASE from prelude output in Step 2. If STATUS is not_detected (unknown agent): proceed to Step 2's custom agent lookup path. If STATUS is error: display REASON and stop.

Step 1: Parse Arguments

The user's input after the command name is: $ARGUMENTS

Extract:

  • skill_name: the first positional argument (required). Two supported formats:
    • <skill-name> — search across all known skill paths
    • <plugin-name>:<skill-name> — search only within the specified plugin's skills directory
  • agent: the value after -a flag (optional). Defaults to auto-detect if not provided.

Agent name as skill_name: If the first positional token exactly matches a known agent name (claude, gemini, codex, openclaw) and no -a flag was given, the user likely meant -a <agent> rather than a skill named after the agent. Silently treat it as the agent specifier: re-run the prelude result with that agent (read ~/.skill-git/config.json), set skill_name to empty, and continue to the missing-skill_name error below which will show the usage message.

Read the full file on GitHub · 454 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 · 454 lines · 0 tokens per session scan A 62ff421fa441

Subscribe to this mod's changes

skill-git:check is a command published in the GitHub repository KnowledgeXLab/skill-git (41 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 4,343 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.