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 artifact-storage-policygit 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/artifact-storage-policy)<a href="https://agentmods.dev/skills/a275618631/codex-antigravity-collaboration/artifact-storage-policy"><img src="https://agentmods.dev/badge/skills/a275618631/codex-antigravity-collaboration/artifact-storage-policy/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/artifact-storage-policy"><img src="https://agentmods.dev/badge/skills/a275618631/codex-antigravity-collaboration/artifact-storage-policy.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 | $0.00068 | $0.01261 |
| Opus 5.5 | $0.00027 | $0.00504 |
| Sonnet 5.5 | $0.00014 | $0.00252 |
| Haiku 4.5 | $0.00007 | $0.00126 |
Grade A, and why
artifact-storage-policy 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 1mo 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
交付物儲存政策
目的
先確認專案、目的地與既有位置，再建立或寫入外部交付物。此 Skill 是工作報告、Google Drive 保存與 GitHub repository 選擇的共同政策；不負責搬移歷史檔案，也不取代平台專用工具。
觸發條件
- 產出或保存工作報告、設定改版、稽核結果或其他正式成果。
- 使用者要求保存到 Google Drive、GitHub，或同時保存到兩者。
- 需要選擇新 repository、專案資料夾或交付目錄。
- 需要判斷是否沿用既有專案、分支或版本。
外部平台分流
- Codex 交付物放在 Google Drive 的
CODEX/<project folder>/；Antigravity 交付物放在其指定 Drive folder；兩者不得互相覆寫。 - GitHub 交付物沿用既有專案 owner/repository 與非保護分支；不要因單一任務建立重複 repository。
- 正式交付、多檔案成果或外部上傳才建立完整交付物索引；單一本機小改且沒有交付要求時，簡短回報即可。
Input Schema
需要建立完整 routing ledger 或交付物索引時，讀取 references/storage-contract.md。一般單一目的地工作不必載入 schema。
Resolution Workflow
- 搜尋既有專案名稱、別名、近期交付物、Drive 資料夾與 GitHub repository；不得只依任務標題猜測。
- 確認 Google Drive 的
CODEX根資料夾 ID、專案資料夾 ID、完整路徑與寫入權限；Drive 根目錄或My Drive根目錄不是合格目的地。 - 確認 GitHub owner、repository、目前分支與既有相關 repository；同一專案優先沿用既有 repository，不因日期或單一任務建立新 repo。
- 判斷關係：
new、continuation、branch或related。若無法判斷，標記needs_review，不得自行建立新位置。 - 檔名使用繁體中文，至少包含專案／功能、用途與建立日期；避免只用
report.md、final.docx、output.txt。 - 寫入後必須讀回 metadata／內容，核對實際 parent、完整路徑、檔名、URL、MIME／大小與 repository／分支。
- 發現錯放、重複、檔名不合規或無法回讀時，狀態為
needs_repair或failed，不得報告為完成。移動、重新命名、覆蓋、刪除或權限變更需另有明確授權。
交付物索引與摘要錨點
- 每次產出、修改、上傳或寄送檔案，都要建立可直接放入最終回覆與工作報告的「交付物索引」；每個檔案一列，不得只列來源或工具名稱。
- 索引至少包含：檔名、用途、本機完整絕對路徑、實際 URL、Drive 完整路徑／parent ID 或 GitHub repository／branch、狀態與驗證結果。
- 本機不存在、尚未保存或無法驗證的欄位必須明確標示
不適用、尚未保存或未驗證；不得推測路徑、組合未回讀的 URL 或把來源資料當成交付物。 - 長任務、上下文壓縮或交接摘要時，優先保留這份索引與未完成項目。若平台摘要 UI 只顯示來源，主要回覆仍必須保留完整索引。
Date and historical-file rules
- 新交付物的檔名使用實際建立日期。
- 同一專案的既有頂層資料夾應沿用；若需要更新頂層日期，先提供舊名／新名／影響範圍並取得明確核准。
- 本 Skill 不自動搬移、重新命名、刪除或覆蓋歷史檔案；錯放項目只列為候選清單，另案處理。
- 新資料夾只有在已確認
CODEX根、專案不存在、關係為new且使用者授權寫入時才能建立。
Fail-closed conditions
任何一項無法確認時停止遠端寫入：CODEX 根、專案識別、目標 parent、repository、沿用／新建關係、寫入權限、寫入後 metadata／URL／內容回讀。
Audit fields
每次交付至少保留：實際使用的 Skill／Workflow／Agent、Drive 完整路徑與 parent ID、GitHub owner/repository/branch、每個 artifact 的檔名與 URL、四層驗證結果、未解決項目。
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.
- 1mo ago Changed · -67 lines 6b64e12c5a76
- 1mo ago First seen · 127 lines · 68 tokens per session scan A 5dc992bfc80e
artifact-storage-policy is a skill published in the GitHub repository a275618631/codex-antigravity-collaboration (11 stars, last pushed 4d ago), licensed MIT. It adds 68 tokens to every session and 1,261 once invoked, about $0.0003 per session on Opus 5.5. 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
review-change
Review a completed change against its authorizing spec in fresh context — evidence-based checks, severity-ranked findings, and a written verdict for the human's merge decision. Use when a diff needs reviewing before merge, or when add-feature / fix-bug / implement-spec reaches its review gate.
mindforge-pause-work
Create context handoff when pausing work mid-phase.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
aident-loadout
Run multi-step work across apps the user connected in Aident Loadout: live action schemas, connection checks, cost preflight, and approval before side effects.
accint-commitments
Triage acc's open promises and close them with honest real-world verdicts via accact(runtime="outcome").
peon-ping-toggle
Toggle peon-ping sound notifications on/off. Use when user wants to mute, unmute, pause, or resume peon sounds during a Claude Code session. Also handles config changes like volume, pack rotation, categories — any peon-ping setting.