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 BENZEMA216/wechat-archive-harness --skill wechat-archivegit clone --depth 1 https://github.com/BENZEMA216/wechat-archive-harnessWrote 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/benzema216/wechat-archive-harness/wechat-archive)<a href="https://agentmods.dev/skills/benzema216/wechat-archive-harness/wechat-archive"><img src="https://agentmods.dev/badge/skills/benzema216/wechat-archive-harness/wechat-archive/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/benzema216/wechat-archive-harness/wechat-archive"><img src="https://agentmods.dev/badge/skills/benzema216/wechat-archive-harness/wechat-archive.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 | $0.00063 | $0.00758 |
| Opus 5 | $0.00032 | $0.00379 |
| Sonnet 5 | $0.00013 | $0.00152 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
wechat-archive 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 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.
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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WeChat Archive
Use this Skill only for the user's own Mac, WeChat account, and local archive. The archive may contain other people's private data. Keep acquisition local and report structure, counts, coverage, hashes, and status by default rather than chat samples.
Before the first operation in a task, read references/safety.md. Read references/operations.md before a sync, verification, or scheduler-related request.
Tool surface
DeepSeek Harness exposes the server tools with the mcp__wechat__ namespace:
mcp__wechat__wechat_doctor: read-only environment and safety diagnosis.mcp__wechat__wechat_status: read-only last-run and archive summary.mcp__wechat__wechat_sync: deterministic local synchronization. This is the only archive-writing tool.mcp__wechat__wechat_verify: read-only integrity and coverage verification.
If the host presents the raw MCP names instead, use wechat_doctor, wechat_status, wechat_sync, and wechat_verify with the same rules.
Required workflow
- Call
wechat_doctorbefore the first sync or whenever the WeChat build, account, source path, signature, or key state may have changed. - Treat these states as stop conditions:
WECHAT_SIGNATURE_UNSAFE,WECHAT_RUNNING,WAL_PRESENT,SECRET_UNAVAILABLE,SOURCE_CHANGED_DURING_DECRYPT,SOURCE_CHANGED_DURING_SYNC,PROCESS_CHECK_FAILED,PERMISSION_DENIED, andLOCKED. - Never work around a stop condition by killing WeChat, re-signing the app, ignoring WAL, changing permissions, guessing an account, or reading a secret. Explain the required human action.
- Call
wechat_synconly after the user explicitly asks to create or refresh the local archive. Pass its explicit confirmation field. Do not infer consent from an analysis or status request. - After a successful or no-change sync, call
wechat_verifybefore reporting success. - Report the exact run status, source scope, counts, coverage equation, unresolved media categories, archive alias, and verification result. Report archived media object/byte counts only when
media_binary_verified=true. Do not report a message sample unless the user separately asks for content analysis.
What ships with it
2 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.
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 · 41 lines · 63 tokens per session scan A 5797c8d154b5
wechat-archive is a skill published in the GitHub repository BENZEMA216/wechat-archive-harness (0 stars, last pushed 16d ago), licensed MIT. It adds 63 tokens to every session and 758 once invoked, about $0.0003 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
frame-macos-notification
Realistic macOS notification banner with app icon, title, and body, suited to video overlays or product teasers.
baocut
BaoCut-only operator for the installed bcut CLI and .bcut projects. Implicitly trigger only when the request explicitly names BaoCut or bcut, targets a .bcut project or BaoCut Subtitle Studio, or continues a BaoCut workflow already established in the conversation. Do not trigger solely for generic audio or video…
starcat-ui-prototype
A design skill for creating macOS interface prototypes and visual designs for Starcat, a GitHub star-management and AI knowledge-organising app. It follows Apple’s Liquid Glass design language for macOS 26.
personal-commands
Edit hex.config.ts, not .hex-sdk. Config and installed dependencies execute with the user's normal permissions; use only trusted packages and avoid network, filesystem, environment, or subprocess access unless the requested command requires it. Run bun run check after editing.
clovy-obsidian
Work with the Obsidian vault currently selected in Clovy.
clarify-intent-and-establish-shared-understanding
Grounded in first principles, rigorously examine and refine a user's plan, task, decision, goal, strategy, proposal, or idea through structured, progressively deeper questioning, in order to bridge the gap between the User and the Agent. Use when the user explicitly requests grilling, challenge, pressure-testing…