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 anymouschina/TapCanvas --skill agents-teamgit clone --depth 1 https://github.com/anymouschina/TapCanvasWrote 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/anymouschina/tapcanvas/agents-team)<a href="https://agentmods.dev/skills/anymouschina/tapcanvas/agents-team"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/agents-team/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/anymouschina/tapcanvas/agents-team"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/agents-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00775 |
| Opus 5 | $0.00016 | $0.00387 |
| Sonnet 5 | $0.00006 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
agents-team 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agents-team
This Skill enables general agents team mode. It is disabled by default and only becomes available after you load this Skill.
Principles
- Only use multi-agent tools when the user explicitly requests team mode, or after this Skill is loaded.
- Always explicitly declare roles by using
agent_type:orchestrator: plan, delegate, and merge.worker: implement a bounded code or execution task.reviewer: do a read-only audit for bugs, regressions, or missing checks.research: summarize sources / produce supporting material.writer: draft a section or structured artifact.editor: unify voice, tighten structure, fix inconsistencies.
- Keep each sub-agent task well-scoped and output-oriented.
- Prefer parallel delegation only for independent work. If one result determines the next step, do not parallelize.
- Use
list_agentsandwaitto observe real team state instead of assuming progress. - When you need to reference a specific dispatched task, track the returned
submission_id, not only theagent_id. - Use
fork_context: trueonly when the child genuinely needs the current conversation context; otherwise keep prompts tighter. - Team children inherit the parent runtime grant for tools/filesystem/network, but runtime strips further subagent spawning (
spawn_agent/ legacyTask). - Do not add blanket constraints like “不要调用任何工具” unless the task truly requires it; role prompts are soft guidance, runtime grant is the hard boundary.
Tools (available only after this Skill is loaded)
spawn_agent({ agent_type, prompt, description?, fork_context? })->{ agent_id, submission_id }wait({ ids, timeout_ms? })-> agent statuses + submission statuses/previewssend_input({ id, prompt, interrupt? })-> queue more work for that agent and return a newsubmission_idresume_agent({ id })-> reopen a closed agent so it can receive future workclose_agent({ id })list_agents()
Recommended Workflow (General Team)
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 · 60 lines · 32 tokens per session scan A 05500e65f096
agents-team is a skill published in the GitHub repository anymouschina/TapCanvas (602 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 775 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
dramake
A production workflow for turning an idea, story, script, storyboard, or existing footage into a short AI drama or film. It covers planning, generation, voice, editing, and quality checks for formats such as vertical and horizontal video.
last30Days
Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…
thisWeek
Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…
short-drama-storyboard
A workflow for turning a Chinese short-drama script and its visual facts into a shot-by-shot storyboard with frozen starting-frame prompts.
md-fetch-summarize
Fetch a URL and return a concise markdown summary of its content. Read-only: no files are written; the summary is returned as output only. Use when asked to "fetch and summarize", "summarize this URL", "what does this page say", or "get the content of ". Proactively suggest when the user pastes a URL and asks what it…
vchart-development-assistant
A coding assistant for VChart, a JavaScript chart library used to build visualizations such as bar, line, and pie charts.