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 skills add XMZF-vAI/clerkbox --skill find-skillsgit clone --depth 1 https://github.com/XMZF-vAI/clerkboxWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xmzf-vai/clerkbox/find-skills)<a href="https://agentmods.dev/skills/xmzf-vai/clerkbox/find-skills"><img src="https://agentmods.dev/badge/skills/xmzf-vai/clerkbox/find-skills/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xmzf-vai/clerkbox/find-skills"><img src="https://agentmods.dev/badge/skills/xmzf-vai/clerkbox/find-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 119 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 123 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 124 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 129 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 192 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 268 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00078 | $0.03074 |
| Opus 5 | $0.00039 | $0.01537 |
| Sonnet 5 | $0.00016 | $0.00615 |
| Haiku 4.5 | $0.00008 | $0.00307 |
Grade A, and why
find-skills 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 11d ago.
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.
**Manual fallback (if the script is unavailable):** download with `curl -fSL -o skill.zip <url>`, extract (PowerShell `Expand-Archive` / `unzip`), locate the directory containing `SKILL.md`, and move it to `~/.clerkbox/s How it starts
The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find Skills
This is ClerkBox's skill discovery & installation orchestration skill. It searches two sources — the ClerkBox built-in skill store (CocoLoop Hub, preferred) and the skills.sh community skill library (secondary) — and merges results into a single search-and-install flow, with mandatory user confirmation before any installation.
CORE PRINCIPLE: Search both sources before presenting results. The built-in store offers curated quality skills; skills.sh covers niche domains and newer tools. Searching only one source is an incomplete search.
Priority: Search First, Then Execute
CRITICAL: When the user requests help with a specialized task, search for available skills FIRST before attempting the task directly with your general capabilities.
The correct behavior is:
- User asks for help with a specialized task (e.g., "help me deploy this", "review my code", "做个 PPT")
- FIRST: search both sources for relevant skills
- Present results to the user and let them pick (see confirmation rule below)
- Install the chosen skill
- THEN: use the installed skill to fulfill the user's original request
Do NOT skip steps 2–4 and jump directly to attempting the task yourself.
Before You Begin: User Confirmation Rule
IMPORTANT: Never install any skill without explicit user confirmation.
ClerkBox has no structured question UI — after searching, present the results as a numbered list in plain text and ask the user to reply with the number(s) to install:
我找到了以下与「<query>」相关的技能：
1. <skill-name>（技能商店）— <一句话描述>；下载量 <N>
2. <skill-name>（技能商店）— <一句话描述>
3. <repo/skill-name>（社区 skills.sh）— <一句话描述>
回复编号即可安装（可多选），或告诉我直接处理任务。
- Present results from all sources that returned matches — "商店在前、社区在后"只是排序，不是过滤。
- Total recommendations MUST NOT exceed 4 — curate the most relevant subset; mention "(还有 N 个相关结果)" if more exist.
- Do NOT install anything until the user explicitly picks.
When to Use This Skill
Use this skill when the user:
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 270 lines · 78 tokens per session scan A bedfa293e4c6
find-skills is a skill published in the GitHub repository XMZF-vAI/clerkbox (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 78 tokens to every session and 3,074 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 2026-08-31.
Other skills, from other repositories
gws-sheets
Google Sheets: Read and write spreadsheets.
gws-sheets-append
Google Sheets: Append a row to a spreadsheet.
gws-sheets-read
Google Sheets: Read values from a spreadsheet.
recipe-create-expense-tracker
Set up a Google Sheets spreadsheet for tracking expenses with headers and initial entries.
recipe-copy-sheet-for-new-month
Duplicate a Google Sheets template tab for a new month of tracking.
recipe-generate-report-from-sheet
Read data from a Google Sheet and create a formatted Google Docs report.