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/installgit 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 | $0.00084 | $0.02247 |
| Opus 5 | $0.00042 | $0.01123 |
| Sonnet 5 | $0.00017 | $0.00449 |
| Haiku 4.5 | $0.00008 | $0.00225 |
Grade A, and why
skill-git:install scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://clawhub.ai/api/v1/search?q=<query>" 2>&1 How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /skill-git:install. Follow these steps exactly.
All output shown to the user must be in English.
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):
- Parse arguments — validate identifier format, derive
install_name, extract agent flag - Init check — run prelude, get AGENT / GLOBAL_BASE / SKILLS_JSON
- Conflict check — verify
install_namenot already installed; setinstall_path - Download skill — fetch files from the registry into
install_path - Preview and confirm — display skill name, description, content preview; ask user to confirm
- Init skill — run
sg-init.shto create git repo, initial commit, and v1.0.0 tag
Step 0 — Parse Arguments
If $ARGUMENTS is empty:
Identifier required.
Usage: /skill-git:install skillhub:<owner>/<repo>@<skill>
/skill-git:install clawhub:<slug>
Use /skill-git:search to find skills first.
Stop.
Extract registry and identifier from the first non-flag token:
skillhub:<owner>/<repo>@<skill>→registry = "skillhub", validateidentifiercontains/and@clawhub:<slug>→registry = "clawhub", validate slug is non-empty with no/or spaces- Unknown prefix →
Unknown registry. Use "skillhub:" or "clawhub:" as prefix.Stop.
On validation failure, extract a best-effort search query from all non-flag tokens (e.g. vercel/agent-browser → agent-browser) and run a registry search to suggest the correct identifier:
SkillHub fallback search:
npx skills find "<query>" 2>&1
ClawHub fallback search:
curl -s "https://clawhub.ai/api/v1/search?q=<query>" 2>&1
Parse the results and present matching skills to the user using AskUserQuestion with one option per result plus a "Cancel" option. Each option label should show the full valid identifier (e.g. skillhub:vercel/agent-browser@agent-browser). If no results are found, show the expected format and stop:
# SkillHub
Invalid SkillHub identifier. Expected: skillhub:<owner>/<repo>@<skill>
# ClawHub
Invalid ClawHub slug. Expected: clawhub:<slug>
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 · 259 lines · 0 tokens per session scan A b0a404c51bf3
skill-git:install is a command published in the GitHub repository KnowledgeXLab/skill-git (41 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 2,247 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.