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.
npx agentmods add commands/knowledgexlab/skill-git/mergegit clone --depth 1 https://github.com/KnowledgeXLab/skill-gitWhat 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 | $0.00062 | $0.05623 |
| Opus 5 | $0.00031 | $0.02812 |
| Sonnet 5 | $0.00012 | $0.01125 |
| Haiku 4.5 | $0.00006 | $0.00562 |
Grade C, and why
skill-git:merge scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf <skill-path> How it starts
The opening of the file, as written. The whole thing — 537 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /skill-git:merge. Follow these steps exactly.
Merge never overwrites anything silently. Every destructive action requires explicit user confirmation before execution.
Task Tracking
You MUST create a task for each item below and update each task's status as you progress (pending → in_progress → completed):
- Resolve skills to merge — parse arguments or select from latest scan results
- Load topics and show overlap — extract/cache rules, cluster into topics, display summary
- Resolve conflicts — present each conflicting topic and record user decisions (skip if none)
- Choose name and base folder — prompt for merged skill name and which folder to use as base
- Synthesize merged SKILL.md — generate draft, show for approval, iterate on edits
- Write files — write SKILL.md, copy non-SKILL.md files, update config.json, delete sources
- Commit merged skill — pre-flight check, confirm, run git add/commit/tag
Prelude
!bash "${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.
- If you can determine intent, note the resolution and proceed.
- If STATUS is
not_initializedand 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.
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 · 537 lines · 0 tokens per session scan C dbb4a86701a0
skill-git:merge is a command published in the GitHub repository KnowledgeXLab/skill-git (41 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 5,623 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.