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 output-contractgit 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/output-contract)<a href="https://agentmods.dev/skills/a275618631/codex-antigravity-collaboration/output-contract"><img src="https://agentmods.dev/badge/skills/a275618631/codex-antigravity-collaboration/output-contract/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/output-contract"><img src="https://agentmods.dev/badge/skills/a275618631/codex-antigravity-collaboration/output-contract.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 | $0.00079 | $0.00596 |
| Opus 5 | $0.00039 | $0.00298 |
| Sonnet 5 | $0.00016 | $0.00119 |
| Haiku 4.5 | $0.00008 | $0.00060 |
Grade A, and why
output-contract 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 10d 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
交付契約
使用時機
在任務完成前啟用，檢查是否已交代使用者需要知道的結果、風險與下一步。
[!TIP] Minimal 免檢疫例外：若任務判定為
Minimal車道 (極簡快車道)，強制豁免產出以下完整的標準收尾區塊。改以一句話精簡總結完成狀態與耗時即可，以達到最高執行效率。
標準收尾
任務追蹤 (Telemetry)
- 工作流路徑 (Routing Path): [例如 Minimal, Standard, Full Orchestrator]
- 各路徑耗時 (Time Spent): [列出各節點/子代理解決問題的耗時]
- 載入的 Skill (Skills Loaded): [列出過程中啟用的 Skill 名稱]
完成狀態
- ...
修改清單
- ...
測試與檢查
- ...
待確認事項
- ...
規則
- 有修改檔案時列出所有檔案；沒有修改寫「無」。
- 有測試或檢查時列出指令/方式與結果；未執行需說明原因。
- 有失敗、跳過、未確認、需人工判斷的事項，明確列出。
- 不把大量檔案內容貼到回覆中；只列路徑、摘要與結果。
- 所有本機路徑與遠端連結，都必須使用可點擊的 Markdown 格式 (例如：
[檔名](file:///C:/絕對路徑))，方便使用者直接點選開啟。 - 本 Skill 負責整理交付回報，不負責判斷成果是否通過內容或風險檢查；需要時另行啟用
checklist-validator。 - 若完成同步、commit、push，列出實際成功的動作。
高風險附加欄位
涉及設定、同步、刪除、遠端、憑證、資料搬移時，加上：
風險與保護
- ...
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.
- 10d ago First seen · 54 lines · 79 tokens per session scan A e44bc0425473
output-contract is a skill published in the GitHub repository a275618631/codex-antigravity-collaboration (8 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 596 once invoked, about $0.0004 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
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
anti-sleep
Keep a Mac awake with caffeinate during long builds, downloads, or supervised automation runs.
ask-questions-if-underspecified
Clarify requirements before implementing. Use when serious doubts arise.
airtable-automation
Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas.
ask-matt
Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.
accint-commitments
Triage acc's open promises and close them with honest real-world verdicts via accact(runtime="outcome").