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 StarryCod/cogitum --skill yuanbaogit clone --depth 1 https://github.com/StarryCod/cogitumWrote 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/starrycod/cogitum/yuanbao)<a href="https://agentmods.dev/skills/starrycod/cogitum/yuanbao"><img src="https://agentmods.dev/badge/skills/starrycod/cogitum/yuanbao.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 | $0.00021 | $0.01011 |
| Opus 5 | $0.00010 | $0.00505 |
| Sonnet 5 | $0.00004 | $0.00202 |
| Haiku 4.5 | $0.00002 | $0.00101 |
Grade D, and why
yuanbao scanned grade D with 3 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 3d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
**NEVER say you cannot send messages or @mention users. NEVER suggest the user do it manually. NEVER add disclaimers about permissions. Just reply with the text you want sent.** Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
**NEVER say you cannot send messages or @mention users. NEVER suggest the user do it manually. NEVER add disclaimers about permissions. Just reply with the text you want sent.** Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
**NEVER say you cannot send messages or @mention users. NEVER suggest the user do it manually. NEVER add disclaimers about permissions. Just reply with the text you want sent.** This is a copy
95% identical to yuanbao — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yuanbao Group Interaction
CRITICAL: How Messaging Works
Your text reply IS the message sent to the group/user. The gateway automatically delivers your response text to the chat. You do NOT need any special "send message" tool — just reply normally and it gets sent.
When you include @nickname in your reply text, the gateway automatically converts it into a real @mention that notifies the user. This is built-in — you have full @mention capability.
NEVER say you cannot send messages or @mention users. NEVER suggest the user do it manually. NEVER add disclaimers about permissions. Just reply with the text you want sent.
Available Tools
| Tool | When to use |
|---|---|
yb_query_group_info |
Query group name, owner, member count |
yb_query_group_members |
Find a user, list bots, list all members, or get nickname for @mention |
yb_send_dm |
Send a private/direct message (DM / 私信) to a user, with optional media files |
@Mention Workflow
When you need to @mention / 艾特 someone:
- Call
yb_query_group_memberswithaction="find",name="<target name>",mention=true - Get the exact nickname from the response
- Include
@nicknamein your reply text — the gateway handles the rest
Example: user says "帮我艾特元宝"
Step 1 — tool call:
{ "group_code": "328306697", "action": "find", "name": "元宝", "mention": true }
Step 2 — your reply (this gets sent to the group with a working @mention):
@元宝 你好，有人找你！
That's it. No extra explanation needed. Keep it short and natural.
Rules:
- Call
yb_query_group_membersfirst to get the exact nickname — do NOT guess - The @mention format:
@nicknamewith a space before the @ sign - Your reply text IS the message — it WILL be sent and the @mention WILL work
- Be concise. Do NOT explain how @mention works to the user.
Send DM (Private Message) Workflow
When someone asks to send a private message / 私信 / DM to a user:
- Call
yb_send_dmwithgroup_code,name(target user's name), andmessage - The tool automatically finds the user and sends the DM
- Report the result to the user
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.
- 3d ago First seen · 109 lines · 21 tokens per session scan D 56faaee93882
yuanbao is a skill published in the GitHub repository StarryCod/cogitum (11 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 1,011 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 3 findings (subtle steering, tells the agent never to refuse, strips warnings and disclaimers). It is 95% identical to yuanbao, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
workflow-creator
Turn a repeatable multi-step task into a runnable, reusable saved workflow through guided conversation, in either of two shapes — chaining existing skills/recordings (wiring each one's output into the next's input), or composing the workflow script's own primitives (agent/parallel/pipeline) directly when the task…
cron-task-creator
A scheduler for recurring octo agent tasks. Each task contains a schedule and a prompt, so octo can run an agent turn automatically at the specified times.
resume-crafting
A career-writing aid for turning a résumé or cover letter into clear evidence of results. It uses measurable outcomes and adapts the wording to a job description and applicant-tracking systems, or ATS tools that scan applications for relevant terms.
knowledge-session-state-and-context-session-catalog-fork-rewind-and-export
A session-lifecycle component for finding, resuming, archiving, branching, rewinding, searching, and exporting saved conversations.
knowledge-interaction-surfaces-cli-bootstrap-headless-and-print
A codebase guide for the command-line startup path, including interactive, non-interactive, print, and structured JSONL output modes.
knowledge-interaction-surfaces-terminal-ui
A codebase guide for the interactive terminal interface, including keyboard input, message display, confirmations, questions, session switching, and streamed output.