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 jianshuo/claude-skills --skill wjs-evaling-voicedrop-promptsgit clone --depth 1 https://github.com/jianshuo/claude-skillsWrote 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/jianshuo/claude-skills/wjs-evaling-voicedrop-prompts)<a href="https://agentmods.dev/skills/jianshuo/claude-skills/wjs-evaling-voicedrop-prompts"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-evaling-voicedrop-prompts/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/jianshuo/claude-skills/wjs-evaling-voicedrop-prompts"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-evaling-voicedrop-prompts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00136 | $0.00823 |
| Opus 5 | $0.00068 | $0.00411 |
| Sonnet 5 | $0.00027 | $0.00165 |
| Haiku 4.5 | $0.00014 | $0.00082 |
Grade A, and why
wjs-evaling-voicedrop-prompts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
VoiceDrop 挖矿 prompt 评估
harness = 本 skill（协议）+ jianshuo.dev agent/eval/（脚本/数据）。运行时 = 本地 Claude Code。
被测对象 = agent/src/prompts/mine.js 的 MINE_SYSTEM（git 即版本库）。
何时用
用户改了挖矿 prompt（MINE_SYSTEM），想用数据判断改好了还是改坏了，而不是凭感觉看一两次。
流程（按序）
- 拿候选 prompt：把候选版
MINE_SYSTEM文本写到一个临时文件（如/tmp/cand-prompt.txt）；冠军 = 当前mine.js的MINE_SYSTEM（脚本自动读）。 - 跑产出：
cd ~/code/jianshuo.dev/agent && CLAUDE_API_KEY=$CLAUDE_API_KEY node eval/run-eval.mjs /tmp/cand-prompt.txt <runId>。产出落eval/runs/<runId>/。先看终端有没有「确定性回退」警告——有就先停，多半是候选 prompt 破坏了 JSON 输出。 - 成对盲评：对每条 fixture，dispatch 一个 subagent，喂
references/judge-rubric.md+ 该 fixture 的 transcript + 两份产出。A/B 顺序随机（一半 fixture 把 candidate 放 A、一半放 B，记录映射，收到结果后还原成 champion/candidate）。裁判模型用与生成（opus）不同家族的模型。收每条的{winner, dims, reason}。 - 聚合：把还原后的
verdicts（winner ∈ candidate/champion/tie）+ 候选 proxyFails 喂aggregate()，渲染renderReport()→ 写eval/runs/<runId>/report.md。 - 人工终审：把胜负最接近、分歧最大的 1–2 条产出并排摆给用户。机器只筛掉明显更差的，文风最后一票是用户。
- 晋级：仅当
decision==="promote"（胜率 ≥70% 且无回退）且用户点「认可」——把候选写回agent/src/prompts/mine.js的MINE_SYSTEM，commit（message 附 runId 与胜率），并跑npm test确认没破坏。否则保留报告、不动生产版。
边界
- 只评挖矿 prompt（
MINE_SYSTEM/MINE_SYSTEM_FORCE）。审核/语音编辑 prompt 是不同 eval 模式，不在本 skill。 - 不测成本/缓存/延迟（本地缓存行为≠生产）；不做无人值守。
- 真实金标集要 ≥10 条才可信（见
agent/eval/fixtures/README.md的补充流程）；种子 2 条只够自测流程。
What ships with it
1 file 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.
- 13d ago First seen · 27 lines · 136 tokens per session scan A a3615d97ccbe
wjs-evaling-voicedrop-prompts is a skill published in the GitHub repository jianshuo/claude-skills (129 stars, last pushed 23d ago), licensed MIT. It adds 136 tokens to every session and 823 once invoked, about $0.0007 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.
Other skills, from other repositories
AI & LLM Security
LLM and AI application security testing — prompt injection, jailbreak resistance, OWASP LLM Top 10 (2025), RAG and agent/tool-use security, model supply chain, and AI red teaming for authorized assessments.
prompt-testing
Use when comparing two prompt variants, defining quality/efficiency/robustness metrics, or deciding whether to adopt a challenger prompt over a baseline.
testing-dbt-models
Adds schema tests and data quality validation to dbt models. Use when working with dbt tests for: (1) Adding or modifying tests in schema.yml files (2) Task mentions "test", "validate", "data quality", "unique", "notnull", or "acceptedvalues" (3) Ensuring data integrity - primary keys, foreign keys, relationships (4)…
mcp-builder
Scaffolds and ships MCP servers in Python (FastMCP) or TypeScript (@modelcontextprotocol/sdk) — tools designed around workflows rather than raw endpoints, with model-guiding schemas and error messages, pagination, a direct-call test harness, and wiring into .mcp.json or claude mcp add. Use when the user says "build an…
llm-campaign-drift-gate
Gate resumption of any multi-day LLM batch-scoring campaign that calls an unpinned model alias (deepseek-chat, gpt--latest, gemini--preview, any provider alias without a pinned version). Use when: (1) resuming a paused or credit-exhausted scoring run days after its last chunk, (2) topping up credits to finish a…
llm-gold-bound-failure-check
Diagnose whether an LLM classifier's validation-gate failure is GOLD-BOUND before spending on prompt revision or model changes. Use when: (1) a scoring pipeline over-predicts a label (precision low, recall high) and a prompt clarification is proposed to tighten it, (2) a pilot/validation gate fails and the fix…