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 curtischoutw/claude-institution --skill done-checkgit clone --depth 1 https://github.com/curtischoutw/claude-institutionWrote 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/curtischoutw/claude-institution/done-check)<a href="https://agentmods.dev/skills/curtischoutw/claude-institution/done-check"><img src="https://agentmods.dev/badge/skills/curtischoutw/claude-institution/done-check/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/curtischoutw/claude-institution/done-check"><img src="https://agentmods.dev/badge/skills/curtischoutw/claude-institution/done-check.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 | $0.00052 | $0.01175 |
| Opus 5 | $0.00026 | $0.00588 |
| Sonnet 5 | $0.00010 | $0.00235 |
| Haiku 4.5 | $0.00005 | $0.00118 |
Grade A, and why
done-check 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.
- 用真實指令實際執行改動的功能(curl、跑 script、開頁面),不是只看程式碼「應該會動」。 What it actually says
done-check:完成前驗證
目的:杜絕「假完成」。每一個 ✅ 都必須有貼出來的指令與輸出當證據;沒有證據就不是 ✅。
執行步驟(依序,不可跳過)
1. 複述完成判準
用一句話寫出這個任務原本的完成判準(來自 tasks/todo.md 或使用者的原話)。
- 如果寫不出具體判準 → 停,先回去確認任務範圍,不要繼續。
2. 跑現有測試
- 先找測試指令:依序檢查
package.json的 scripts、Makefile、pyproject.toml、CI 設定檔(.github/workflows/)。 - 跑它,貼出輸出最後 10 行。
- 找不到任何測試 → 明確寫「本專案無測試」,不要假裝跑過。
- 測試失敗 → 不是完成。回去修,或如實回報失敗內容。
3. 手動走 happy path
- 用真實指令實際執行改動的功能(curl、跑 script、開頁面),不是只看程式碼「應該會動」。
- 貼出實際輸出。
4. 走至少 2 個邊界情況
從這個清單挑與改動相關的:空輸入、超長輸入、不存在的檔案/ID、權限不足、重複執行(冪等性)、並發、非 ASCII 字元。
- 每個邊界情況:一行寫「輸入 → 預期 → 實際」。
5. 檢查沒有新的警告或錯誤
- 重看步驟 2–4 的輸出有無 warning / error / deprecation。
- 有 log 檔就 tail 一下。
6. 審視 diff
git diff --stat(或比對改動清單),確認:- 沒有除錯碼(console.log、print、註解掉的程式碼)
- 沒有與任務無關的檔案被改到
- diff 大小與任務規模相稱(小任務出現大 diff = 警訊,回報它)
7. Staff engineer 之問
自問:「一位資深工程師會核准這個 PR 嗎?」有任何遲疑 → 把遲疑的點寫進回報,不要吞掉。
回報格式(固定模板)
## 驗證報告
- 完成判準:<一句話>
- 測試:✅/❌/無測試 — <指令> → <輸出尾行>
- Happy path:✅/❌ — <指令> → <實際輸出>
- 邊界情況:
- <輸入> → 預期 <X> → 實際 <Y> ✅/❌
- <輸入> → 預期 <X> → 實際 <Y> ✅/❌
- 新警告/錯誤:無 / <內容>
- Diff:<N 檔 / M 行>,無除錯碼、無無關改動
- 未驗證項目:<誠實列出,說明原因>
- 已驗證: <hard-rules #3;本輪未引用使用者陳述的程式碼事實則寫「不適用」>
- 範圍外發現: <hard-rules #4;記到 tasks/todo.md 的項目,或「無」>
- AUTH: 使用者說「<原話>」<judgment.md §1;本輪無不可逆動作則寫「不適用」>
上面最後三行是逐字必填欄位,不是可省略的過程細節(reporting.md §2 末段)。
鐵則
- 任何一項標 ⚠️ 未驗證都可以,但用 ✅ 包裝沒驗證過的項目是最嚴重的違規。
- 這份報告是給使用者的回報主體,不是附錄。
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 · 73 lines · 52 tokens per session scan A fdc290340b9d
done-check is a skill published in the GitHub repository curtischoutw/claude-institution (5 stars, last pushed 10d ago), licensed MIT. It adds 52 tokens to every session and 1,175 once invoked, about $0.0003 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
fable-judge
Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model…
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
tmux-real-user-testing
A real-user test workflow for Qwen Code's terminal interface, using tmux to drive the program and capture readable screen snapshots. tmux is a tool for running and observing terminal sessions.
qa-testing
Verify your work by actually operating the app or website you changed, instead of assuming it works. Strongly recommended whenever you build, modify, or debug a web app, website, or desktop GUI app. Drive real browsers with the agent-browser CLI and native desktop apps with the cua-driver CLI. These are installed on…
agent-reproduce-align
Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal traces, compare request bodies, tool/function schemas, outputs, and iterate until the reproduced behavior is close enough.