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 skills/yogasw/wick/wick-pluginsnpx skills add yogasw/wick --skill wick-pluginsgit clone --depth 1 https://github.com/yogasw/wickWhat 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 | $0.00076 | $0.01262 |
| Opus 5 | $0.00038 | $0.00631 |
| Sonnet 5 | $0.00015 | $0.00252 |
| Haiku 4.5 | $0.00008 | $0.00126 |
Grade A, and why
wick-plugins 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using wick plugins
A plugin is a connector shipped as a standalone binary. wick downloads it, verifies it, and runs it in its own process, talking over gRPC. Installing or updating one needs no core rebuild and no restart.
From the LLM's side a plugin connector is indistinguishable from a built-in one — same tool_id shape, same encrypted fields, same audit trail, same tag-based access control. The difference is purely packaging.
Choosing the right connector form
| Connector module | Custom connector | Plugin | |
|---|---|---|---|
| Lives in | Go code compiled into wick | A database row (admin UI) | A separate binary |
| Runs | In the wick process | In the wick process | Its own subprocess (gRPC) |
| Add / update | Code change + redeploy | Edit in UI, click Reload | install / bump version |
| Versioned | With the core | With the database | Independently |
Reach for a plugin when the connector should release on its own schedule or be distributable through the marketplace. For something that ships inside the app, write a connector module. For a no-code definition, use a custom connector.
Installing
Plugins are managed from the app binary, not the dev CLI:
<app> plugin search # browse the marketplace catalog
<app> plugin install slack # download + verify + install by name
<app> plugin list # installed, version, arch, signature, enabled
<app> plugin disable slack # turn off without removing
<app> plugin enable slack
<app> plugin remove slack
Every install verifies before wiring in: the binary's sha256 must match its manifest, the OS/arch must match the host, and when a trusted key is configured the signature must check out. A hot-reload poller picks up any change within a few seconds — no restart.
You can install without the catalog too:
<app> plugin install ./my-connector/ # a built {binary, plugin.json} dir
<app> plugin install https://example.com/foo-0.1.0-linux-arm64.zip
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 · 103 lines · 76 tokens per session scan A de8a692b2be0
wick-plugins is a skill published in the GitHub repository yogasw/wick (5 stars, last pushed 4d ago), licensed MIT. It adds 76 tokens to every session and 1,262 once invoked, about $0.0004 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
golden-rss
Use when testing the rss golden build.
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
studio
Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.
mnemon
Persistent memory for MiniMax Code. Recall durable context, store important facts and decisions, and link related memories with the mnemon CLI.