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 agentmods add skills/nickolaslin33/agent-skills/reentrynpx skills add nickolaslin33/agent-skills --skill reentrygit clone --depth 1 https://github.com/nickolaslin33/agent-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/nickolaslin33/agent-skills/reentry)<a href="https://agentmods.dev/skills/nickolaslin33/agent-skills/reentry"><img src="https://agentmods.dev/badge/skills/nickolaslin33/agent-skills/reentry.svg" alt="Measured on agentmods" 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 | $0.00373 | $0.05178 |
| Opus 5 | $0.00187 | $0.02589 |
| Sonnet 5 | $0.00075 | $0.01036 |
| Haiku 4.5 | $0.00037 | $0.00518 |
Grade A, and why
reentry 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
重新進入工作狀態
這個 skill 要解決的問題
人與 AI agent 工作了一整天，隔天或幾天後再回來接手時，失去的往往不只是「我忘了做到哪裡」「接下來要做什麼」。
真正需要重建的資訊可以分成四類，而且每一類遺失的方式、恢復的方法都不同：
| 是什麼 | 能否重建 | |
|---|---|---|
| 任務狀態 | agent 改了什麼、跑了什麼 | 可以，從 git diff 重建 |
| 決策脈絡 | 為什麼選擇這個做法、曾排除哪些方案 | 沒有留下紀錄的話，通常很難完整還原 |
| 下一步 | 接下來要做什麼 | 有時記在其他地方，有時只存在人的記憶裡 |
| 理解程度 | 人對目前工作內容實際理解到什麼程度 | 無法只靠程式碼或紀錄直接重建 |
前三項描述的是任務本身的狀態，最後一項描述的是人對任務的理解狀態。
最關鍵的是最後一項。在還沒真正理解前就讓任務往下推進，後續工作會建立在不完整的 理解上，之後補回來的成本愈來愈高。這類尚未補足的理解稱為理解債。
所以交接紀錄要完整到隔一段時間之後，只靠它就能重新理解當時的工作狀況，不能只當
提示用。每條規則的研究依據見 references/evidence.md。
環境
以下 $SKILL_DIR 指本 skill 的安裝目錄，依你的環境代入實際路徑。腳本一律用 python3 呼叫，不依賴執行位元、PATH 或任何特定 agent 的機制。只用 Python 3 標準函式庫。
資料放在 $REENTRY_ROOT（預設 ~/reentry），按專案拆資料夾：
~/reentry/
├── orders-api/
│ ├── handoff.md # 工作接續紀錄，每次重新建立
│ ├── artifacts.md # 任務狀態，腳本與 agent 合寫，每次重新建立
│ ├── debt.md # 理解債（以為自己懂但沒懂），保留尚未理解的項目
│ ├── open-questions.md # 待確認（知道自己不知道），保留尚未查清的問題
│ └── decisions/ # 決策紀錄，逐筆保留
└── billing-service/
只有已登記的專案才納入管理。沒有對應資料夾的專案視為未登記，刪除資料夾等於取消登記。不要自動建立或恢復資料夾。
格式規範在 references/file-formats.md，寫任何一個檔案之前先讀它。
先判斷目前處於哪個階段
- 使用者隔了一段時間回來，準備繼續先前的工作 → 回來階段，參考下方「回來時」
- 使用者準備結束這次工作，或剛檢視完 agent 的一批產出 → 收工階段，參考下方「收工時」
回來時
這個階段不需要重新分析或整理內容，只要執行腳本，並將結果原樣提供給使用者。
如果使用者尚未指定專案，先執行索引腳本，列出可接續的專案供他選擇：
python3 "$SKILL_DIR"/scripts/reentry_index.py
指定專案之後：
python3 "$SKILL_DIR"/scripts/reentry_read.py <專案名>
腳本輸出的內容必須完整保留，不要改寫、摘要或重新排版。
使用者自己的用詞是他最好的回憶線索，換句話說等於把線索抽掉；而每次輸出長得一樣， 他才建立得起「打開就知道哪裡看什麼」的習慣。
輸出順序固定如下：
警告（若有）→ 上次叫它做什麼、做到哪裡 → 上次的決定（若有）→ 欠債 → 待確認（若有）→ 下一步
下一步壓在最後是刻意的——避免還沒掌握前因後果就直接繼續往下做。
「上次的決定」只在上次收工真的寫了 decisions/ 才顯示。永遠留一個空欄位會退化成
每次略過的噪音。
腳本最後會顯示一句：「先用自己的話說一次下一步，再開始動手」。
這句只是提醒。不要追問、不要要求他打字、不要確認他有沒有做——他回來時已經準備 動手了，這時候加摩擦只會讓他關掉整套流程。
收工時
整個收工流程大約五分鐘，並直接整合進使用者原本的 review 流程。
這個數字是建議不是上限。它要擋的是兩件事：拖太久，以及卡在回想上出不來。 如果使用者對今天做的事很有想法、想寫得詳細，那不是問題——紀錄詳細本身沒有壞處， 不要因為時間到了就催他收尾。
第一階段 — 請使用者關閉工作畫面，憑記憶整理
請使用者先離開目前的工作畫面，再憑記憶寫下四項內容。寫進 handoff.md 時的標題必須逐字用這四個——腳本靠標題原文解析，改了字就讀不到，而且不會報錯：
What ships with it
27 files 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.
- assets/templates/debt.md 29 B
- assets/templates/decision.md 129 B
- assets/templates/handoff.md 173 B
- assets/templates/open-questions.md 29 B
- README.md 9.5 KB
- references/evidence.md 9.8 KB
- references/file-formats.md 8.1 KB
- references/verifier-prompt.md 4.4 KB
- scripts/reentry_artifacts.py 18 KB runs code
- scripts/reentry_common.py 13 KB runs code
- scripts/reentry_index.py 6.6 KB runs code
- scripts/reentry_read.py 14 KB runs code
- tests/fixture/deploy-cli/artifacts.md 495 B
- tests/fixture/deploy-cli/debt.md 381 B
- tests/fixture/deploy-cli/handoff.md 628 B
- tests/fixture/orders-api/artifacts.md 375 B
- tests/fixture/orders-api/debt.md 141 B
- tests/fixture/orders-api/decisions/2026-08-10-migration版本記在DB.md 368 B
- tests/fixture/orders-api/handoff.md 359 B
- tests/fixture/orders-api/open-questions.md 270 B
- tests/fixture/storefront-web/debt.md 153 B
- tests/fixture/storefront-web/decisions/2026-07-22-地圖底圖改用CartoDB.md 419 B
- tests/fixture/storefront-web/handoff.md 389 B
- tests/test_artifacts.py 23 KB runs code
- tests/test_common.py 17 KB runs code
- tests/test_index.py 24 KB runs code
- tests/test_read.py 32 KB runs code
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.
- 6d ago First seen · 302 lines · 373 tokens per session scan A 0c4523cbf071
reentry is a skill published in the GitHub repository nickolaslin33/agent-skills (2 stars, last pushed 18d ago), licensed MIT. It adds 373 tokens to every session and 5,178 once invoked, about $0.0019 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.