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/searchgit 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 | $0.00066 | $0.05018 |
| Opus 5 | $0.00033 | $0.02509 |
| Sonnet 5 | $0.00013 | $0.01004 |
| Haiku 4.5 | $0.00007 | $0.00502 |
Grade A, and why
skill-git:search 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.
From `search_query`, extract 2–3 meaningful keywords by removing stop words and generic terms (e.g. "a", "the", "find", "skill", "功能", "一个", "做", "帮我"). Each keyword may be a single word or a two-word phrase — never thre How it starts
The opening of the file, as written. The whole thing — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /skill-git:search. 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):
- Detect intent — parse $ARGUMENTS to determine mode, agent, and search query
- Init check — validate local skill exists (similar mode only)
- Build search query — use $ARGUMENTS directly (query mode) or extract from local skill (similar mode)
- Search registries — query SkillHub and ClawHub in parallel
- Enrich ClawHub results — fetch download counts from detail endpoint (similar mode: also filter locally installed skills)
- Filter and rank — score candidates, select top 5
- Present results — display summary table and detail blocks
- Offer to install — prompt user to pick and install a result
Step 0 — Intent Detection
Interpret $ARGUMENTS as natural language. Determine:
-
mode:
queryorsimilarsimilarif the user references a local skill they want to find online equivalents for (e.g. "something like my code-review", "类似我本地 tdd 的", "enhance my humanizer")queryotherwise (user describes what they want to find)
-
similar_skill: the local skill name, if mode =
similar; otherwise null -
search_query: the search keywords, if mode =
query; for similar mode, this is not set here — it is built in Step 2 -
agent: which agent's skill directory to use (default:
claude; detect from phrases like "for gemini", "gemini 的", "on codex", etc.) — detected in all modes for consistency, but only used to resolve skill paths in similar modeagent base_dir claude~/.claudegemini~/.geminicodex~/.codexopenclaw~/.openclaw
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 · 474 lines · 66 tokens per session scan A bca0275293cc
skill-git:search is a command published in the GitHub repository KnowledgeXLab/skill-git (41 stars, last pushed 4mo ago), licensed MIT. It adds 66 tokens to every session and 5,018 once invoked, about $0.0003 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.