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.
git clone --depth 1 https://github.com/PsychQuant/che-apple-mail-mcpWrote 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/commands/psychquant/che-apple-mail-mcp/archive-mail-tree)<a href="https://agentmods.dev/commands/psychquant/che-apple-mail-mcp/archive-mail-tree"><img src="https://agentmods.dev/badge/commands/psychquant/che-apple-mail-mcp/archive-mail-tree/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/commands/psychquant/che-apple-mail-mcp/archive-mail-tree"><img src="https://agentmods.dev/badge/commands/psychquant/che-apple-mail-mcp/archive-mail-tree.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 | $0.00025 | $0.02166 |
| Opus 5.5 | $0.00010 | $0.00866 |
| Sonnet 5.5 | $0.00005 | $0.00433 |
| Haiku 4.5 | $0.00003 | $0.00217 |
Grade A, and why
archive-mail-tree 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
階層歸檔
本命令處理已登錄目標,使用 archive_registry.py 與 archive_distribution.py,不是把目錄名字當成分類規則。未登錄者回原 archive-mail;不自動建立 registry。
階段清單
建立並逐項更新工作清單:驗證 registry/scope;搜尋與去重;目的地預覽;完整 staging;執行或 resume;所有受影響目標 reconcile;報告。任一步未完成不得回報整體成功。
1. 範圍、搜尋與歷史
- 用 registry helper 的 snapshot 讀取所選目標的整個組織樹。缺少/損壞 index 即停止,不以空歷史繼續。保留 JSON 快照、index 指紋及 locations 至本輪結束。
- 本命令未另限 filter 時,各目標依自己 config 的 filters 搜尋,因為父層 filter 不保證包含子層。從原
/archive-mail <filter> <output>轉入時,保留原本已授權的 filter/範圍,不默默搜尋其餘所有 config。需要擴大 corpus 時先顯示範圍並取得使用者同意。 - 搜尋、sender/recipient 判斷、refinement、false-positive scan、草稿處理及 Message-ID 正規化沿用
archive-mail.mdSteps 1.4、1.5、3–4 的程序;以每個目標自己的 config 和共同 identity alias 結果執行。這是引用程序,不要遞迴呼叫 /archive-mail。 - 各層候選以真實 Message-ID 去重,再排除 snapshot.history 的全部鍵(包含 tombstone),即使 local 設
last_archived也必須做 registry 去重。date-only 策略仍可作額外篩選,不能取代已知 ID 歷史。 - 樹內目標由 registry index 負責;
distributed_archives若解析到樹內 output,略過重複掃描。樹外目錄沿用原 Step 2.1 的只讀額外 dedup,缺目錄仍警告。不從 distributed_archives 反向建立 parent。 - 已在 history 的信只回報位置及 index-only 狀態,不重抓補檔。這不阻擋保留「父 filter 沒抓到、child 才發現」且 history 沒有的新信。
2. 目的地預覽
為每個新 Message-ID 寫 candidates JSON;matched_target_ids 只放已確認分類判準命中的目標,沒把握放 []。同名 collaborator 或 filter 命中不是自動歸屬證據。以 helper plan 產生 plan.json。
預覽必須逐項列出信件、發現來源、capture root、最後目的地與判斷理由。跨支線歧義留共同祖先 intake,無匹配留 root intake。先依既有 confirmation-protocol 取得這份 corpus/目的地映射的授權;先前只批准單一 workspace 的動作,不能當成額外子樹寫入授權。沒有新信則報告既有位置/去重結果後結束,不呼叫 execute。
3. 完整 staging(尚未寫入歸檔目標)
- 在獲准的 workspace 下建立專用、一般名稱的暫存目錄,例如
archive-stage-<uuid>,以檔案 API 建立,所有路徑作為資料引數。不能在$HOME/.claude等 export 禁止位置繞過工具政策。 - 引用原 Steps 5、5.5 的完整本文匯出、附件清單與下載程序,輸出改為 stage。此時不更新任何目標 index/threads。凍結六欄 frontmatter 與 verbatim body,不能為方便分派改寫內容。
- 檔名由已支援的
filename_style: archive-mail或原 Date-header 同源 fallback 產生。先檢查預計 intake/目的地皆沒有同名檔,且各目標 index 的歷史 entry(含 tombstone)沒有保留該檔名;以大小寫與 Unicode 等價比較。碰撞時依原命名規則另取-N,更新預覽與 manifest。executor 永不覆寫既有檔。 - 每封所有 explicit/inline 附件均下載到 stage 內,使用原 safe leaf 與 Markdown label/URL encoding 規則。只使用標準 inline links:
[label](URL-encoded-relative-path)或;不帶 title、不用 reference-style,不留下同附件的./...等另一拼法。不要改與附件無關的原始信件內文連結;若無法安全準備,停止該項並揭露。 - manifest 必須列出全部已列舉附件。任何附件下載失敗、內容為 partial/header-only、真實 Message-ID 未確認,皆不得提交該封為完整 capture;保留 stage 與錯誤供重試,不用空 attachments 假裝成功。
- 分別讀 root 與目的地 config 的有效 attachment_routing(#334 逐欄覆寫);將每個附件的 intake_path/destination_path 設為該目標 workspace 相對路徑,或明確登錄 attachment_roots 內的絕對路徑。暫存位置不必與最終位置相同;executor 會依對應清單改寫已知附件 URL。
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 · 71 lines · 25 tokens per session scan A b9b0f5aaa7e7
archive-mail-tree is a command published in the GitHub repository PsychQuant/che-apple-mail-mcp (10 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 2,166 once invoked, about $0.0001 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 2026-10-30.
Other commands, from other repositories
Manage macOS Mail.app - list, read, search, send, reply, update flags, move, delete, and verify sender authentication.
reminders
Manage macOS reminders - list, search, create, complete, update, delete with filtering and batch operations.
contacts
Manage macOS contacts - list, search, get details, create, update, delete.
remind
Create a reminder from natural language.
week
Show this week's calendar overview.
today
Show today's calendar events and pending reminders.