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 CES-Ltd/TitanX --skill weixin-file-sendgit clone --depth 1 https://github.com/CES-Ltd/TitanXWrote 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/ces-ltd/titanx/weixin-file-send)<a href="https://agentmods.dev/skills/ces-ltd/titanx/weixin-file-send"><img src="https://agentmods.dev/badge/skills/ces-ltd/titanx/weixin-file-send/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/ces-ltd/titanx/weixin-file-send"><img src="https://agentmods.dev/badge/skills/ces-ltd/titanx/weixin-file-send.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 | $0.00032 | $0.00491 |
| Opus 5 | $0.00016 | $0.00246 |
| Sonnet 5 | $0.00006 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
weixin-file-send 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 9d 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
Weixin File Send
Use this skill when:
- The user asks you to send a file or image back, for example:
- "send me the file"
- "send the image over"
- "pass the file to me"
- "发给我"
- "图片发过来"
- "把文件传给我"
- A local file already exists and should be delivered to the current chat.
Do not claim a file was sent unless you emit the protocol block exactly. Without the protocol block, the app will not actually send the file.
Protocol
Append one or more protocol blocks at the end of the final reply:
[AIONUI_CHANNEL_SEND]
{"type":"image","path":"./output/chart.png","caption":"Chart ready"}
[/AIONUI_CHANNEL_SEND]
[AIONUI_CHANNEL_SEND]
{"type":"file","path":"./output/report.pdf","fileName":"report.pdf","caption":"Report ready"}
[/AIONUI_CHANNEL_SEND]
Rules
typemust beimageorfile.pathmust point to a real local file that already exists.- Use relative paths when the file is inside the workspace.
fileNameis optional forfile.captionis optional.- If the user clearly wants the file or image sent back, prefer emitting the protocol block instead of only describing the file in text.
- Place protocol blocks after the user-visible answer.
- Do not wrap the JSON in Markdown code fences.
- Do not emit the protocol block if the file does not exist.
- Do not say the file was sent if you did not emit the protocol block.
Examples
User-visible text with image:
I generated the chart and sent it below.
[AIONUI_CHANNEL_SEND]
{"type":"image","path":"./output/chart.png","caption":"Sales chart"}
[/AIONUI_CHANNEL_SEND]
File only:
[AIONUI_CHANNEL_SEND]
{"type":"file","path":"./output/report.pdf","fileName":"report.pdf","caption":"Weekly report"}
[/AIONUI_CHANNEL_SEND]
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.
- 9d ago First seen · 72 lines · 32 tokens per session scan A 56cfc1ac8183
weixin-file-send is a skill published in the GitHub repository CES-Ltd/TitanX (48 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 491 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
dd-verification
Verify claims in pitch decks and founder statements using multiple independent sources. Use when analyzing any claim about market size, traction, team background, or competitive positioning.
ops-desk
Operate a project, workspace, or account from an agent or manager dashboard: inspect state, triage risks, prepare governed actions, route to the right skill lane, require approvals for consequential acts, and verify receipts after execution.
sourcey
Generate documentation for a project using Sourcey.
data-store
Govern provider-agnostic data reads and state transitions through declared data-source operations, not model-authored raw queries.
audit-receipt
Audit a sealed runx receipt for governance, comparing exercised authority and any declared approval requirement with signed evidence, and flag over-reach, approval inconsistency, unrecorded refusals, or exposed secret material.
business-ops
Route one business signal through a replayable governed ops graph: classify, docs, release, work, outreach, spend, and proof, with consequential actions stopping at the right gate.