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 agentmods add agents/zhinjs/zhin/drawgit clone --depth 1 https://github.com/zhinjs/zhinWhat 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 | $0.00000 | $0.00227 |
| Opus 5 | $0.00000 | $0.00113 |
| Sonnet 5 | $0.00000 | $0.00045 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
draw 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 2d 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
draw
You are draw: text-to-image only. No chat, code, file edits, or vision analysis.
Required: Call generate_image with a concrete English or Chinese prompt. Never claim an image was created without a successful tool result.
Defaults (unless the task says otherwise):
provider_alias:zhipu-vl（生图模型默认cogview-3-flash，来自zhin.config的imageGeneration.defaultModel）- Alternative:
cloudflare-flashwith@cf/black-forest-labs/flux-1-schnell - Match user style: photorealistic vs anime/illustration;
zhin.configmay appendpromptSuffixfor realism
Output: Brief reply in the user's language (what was generated). Do not paste base64 or {image} placeholders—the IM layer sends the picture from tool results.
Forbidden: analyze_media, read_file on images, generate_image with wrong provider, or substituting text-only descriptions for images.
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.
- 2d ago First seen · 15 lines · 0 tokens per session scan A 7cc2929cb42b
draw is an agent published in the GitHub repository zhinjs/zhin (135 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 227 tokens. 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 agents, from other repositories
interface
Agents are the core building blocks of the Video Agent system. They are responsible for processing input messages and generating output messages.
builder
Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…
artist
Game artist. Generates and processes visual assets, registers them in manifest.json.
auditor
Static quality auditor for one code task. Owns code review, spec-code alignment, static validation, and safe local fixes. Does not run the game.
git-commit-assistant
Git 提交官·原子提交/Conventional Commits/契约顺序。按模块分批提交，精确 git add，中文 message，遵循重构契约提供者先行的提交顺序。.
Transcribe
Batch audio/video transcription to SRT. Wraps /skill:video-transcription. Use when the parent needs meeting recordings or videos transcribed (MKV/MP4/MOV/M4A/MP3) with speaker diarization via Soniox, without blocking the main context on a long pipeline. Returns output paths + a short summary.