What is skill-git:delete?

A command for permanently removing a registered coding-agent skill from disk and from its configuration file. It first requires selecting the skill and confirming the deletion.

Use it to delete or uninstall a registered skill, after checking its selection and confirming the requested removal.

It removes an unwanted skill and helps prevent accidental deletion by requiring explicit confirmation.

skill-git:delete — 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/delete

Clone the repo

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

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,300 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	$0.00048	$0.01300
Opus 5	$0.00024	$0.00650
Sonnet 5	$0.00010	$0.00260
Haiku 4.5	$0.00005	$0.00130

Measured yesterday against content hash 2ec9710f409d, 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:delete 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/delete.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

Tool Loading

Before doing any work, load all required tools in a single ToolSearch call:

select:TaskCreate,TaskUpdate,TaskList,AskUserQuestion

Do not issue multiple ToolSearch calls.

Task Tracking

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

Select skill — parse arguments or present interactive list
Confirm deletion — show warning and wait for explicit user confirmation
Execute deletion — call sg-delete.sh --execute
Report result — display outcome to user

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 or implicit default).
If STATUS is not_initialized and INITIALIZED_AGENTS is non-empty, suggest /skill-git:init -a <agent>.
If STATUS is not_initialized and INITIALIZED_AGENTS is empty, tell the user to run /skill-git:init first.
If STATUS is error, display REASON as a plain-language error and stop.

Use AGENT, GLOBAL_BASE, and SKILLS_JSON from prelude output for all subsequent steps.

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>.

Step 1 — Select Skill

If a skill name is provided in $ARGUMENTS:

Run:

bash "${CLAUDE_PLUGIN_ROOT}/scripts/sg-delete.sh" --info "<skill_name>" "<global_base>" '<skills_json>'

If STATUS=not_found, tell the user:

Skill "<skill_name>" is not registered.
Run /skill-git:list to see all registered skills.

Then stop.

Use the returned SKILL_PATH, SKILL_VERSION, IS_SYMLINK, IS_DIRTY, DIRTY_SUMMARY for the next step.

If no skill name is provided:

Run:

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

Read the full file on GitHub · 145 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 · 145 lines · 0 tokens per session scan A 2ec9710f409d

Subscribe to this mod's changes

skill-git:delete is a command published in the GitHub repository KnowledgeXLab/skill-git (41 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 1,300 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.

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

skill-git:delete

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Tool Loading

Task Tracking

Prelude

Step 1 — Select Skill

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement