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 a275618631/codex-antigravity-collaboration --skill skill-evaluatorgit clone --depth 1 https://github.com/a275618631/codex-antigravity-collaborationWrote 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/a275618631/codex-antigravity-collaboration/skill-evaluator)<a href="https://agentmods.dev/skills/a275618631/codex-antigravity-collaboration/skill-evaluator"><img src="https://agentmods.dev/badge/skills/a275618631/codex-antigravity-collaboration/skill-evaluator/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/a275618631/codex-antigravity-collaboration/skill-evaluator"><img src="https://agentmods.dev/badge/skills/a275618631/codex-antigravity-collaboration/skill-evaluator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00065 | $0.00532 |
| Opus 5 | $0.00032 | $0.00266 |
| Sonnet 5 | $0.00013 | $0.00106 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
skill-evaluator 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 9d 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
Skill 評估器
目標
用可比較的方式優化 skill，而不是憑感覺改。優先提升觸發準確率、可用率、輸出一致性、token 效率與安全性。
評估流程
- 讀取現有 skill 的
name、description、核心流程與輸出格式。 - 讀取候選 skill 或官方範例，只吸收明顯更好的設計，不照搬無關內容。
- 用以下維度比較：觸發準確、步驟清楚、輸出契約、驗證方式、token 成本、安全邊界、可重用資源。
- 產生 5-10 個真實測試 prompt：包含 should-trigger、should-not-trigger、模糊口語、近似但不該觸發情境。
- 若能執行測試，做舊版 vs 新版比較；不能執行時，至少做人工靜態檢查。
- 修改 skill 時保持精簡；把長參考移到
references/，把重複程式放到scripts/。
比較表格式
| 項目 | 目前版本 | 候選優點 | 是否吸收 | 理由 |
|---|
修改原則
description是主要觸發機制，要包含「做什麼」與「何時用」。- Body 只放執行方法，不重複大段觸發條件。
- 避免過多 MUST / NEVER；能解釋原因時用原因引導。
- 若某步驟每次都重寫，改成 script 或明確模板。
- 不新增與任務無關的 README、CHANGELOG 或說明雜檔。
完成回報
列出：修改的 skill、吸收了哪些優點、未吸收項目與理由、測試/檢查結果、待確認事項。
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.
- 9d ago First seen · 37 lines · 65 tokens per session scan A 5f3560010bfb
skill-evaluator is a skill published in the GitHub repository a275618631/codex-antigravity-collaboration (8 stars, last pushed 10d ago), licensed MIT. It adds 65 tokens to every session and 532 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
architecture-decision-records
Comprehensive patterns for creating, maintaining, and managing Architecture Decision Records (ADRs) that capture the context and rationale behind significant technical decisions.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
aws-sst-development
SST v4 (Ion) expert for managing AWS resources as code with the Pulumi-backed framework.
autonomous-agent-patterns
Design patterns for building autonomous coding agents, inspired by Cline and OpenAI Codex.
peon-ping-log
Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".
conductor-implement
Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.