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 yogasw/wick --skill wick-pluginsgit clone --depth 1 https://github.com/yogasw/wickWrote 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/yogasw/wick/wick-plugins)<a href="https://agentmods.dev/skills/yogasw/wick/wick-plugins"><img src="https://agentmods.dev/badge/skills/yogasw/wick/wick-plugins/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/yogasw/wick/wick-plugins"><img src="https://agentmods.dev/badge/skills/yogasw/wick/wick-plugins.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 | $0.00000 | $0.03569 |
| Opus 5.5 | $0.00000 | $0.01428 |
| Sonnet 5.5 | $0.00000 | $0.00714 |
| Haiku 4.5 | $0.00000 | $0.00357 |
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 today.
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 — 217 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, tool, job, or service shipped as a standalone binary. wick downloads it, verifies it, and runs it in its own process. 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.
The four kinds
| Kind | Lifetime | Reached by | Notes |
|---|---|---|---|
| connector | on demand, idle-killed | the LLM via wick_execute |
gRPC |
| job | spawned per run (cron / Run now), killed when Run returns |
the scheduler | gRPC Job; shows on the Jobs page |
| tool | spawned on first request (held ≤10 s, then 503), idle-killed | users at /tools/{key} |
HTTP over a unix socket, proxied by wick; "plugin" badge on the home grid; KeepWarm for fast webhooks |
| service | always on, restarted with backoff 1s→30s | outside systems at /x/{key}/* |
per-route auth public / token / session; admin page Manager → Services → {key} (status, last 200 log lines, config, access token) |
Installed under <data dir>/plugins/{connectors,jobs,tools,services}/<key>/. Plugin keys use _, never - — so a built-in tool text-counter moved to a plugin becomes /tools/text_counter.
Replacing a built-in (Replaces)
When a plugin takes over an existing tool or job under a new key (built-in notion-ticket-sync → plugin notion_ticket_sync), the plugin declares the old key so it is a replacement, not a new item:
job.Meta{Key: "notion_ticket_sync", Replaces: []string{"notion-ticket-sync"}, ...} // job plugin
tool.Tool{Key: "text_counter", Replaces: []string{"text-counter"}, ...} // tool plugin
It lands in plugin.json (job.meta.Replaces / tool.meta.replaces). On the next boot wick, once per old→new pair:
- copies config fields whose key the plugin also declares — secrets as the stored ciphertext, never decrypted. A field already set on the plugin is kept; only an empty field, or a non-secret still at the plugin default, is filled. A field whose secret flag differs is skipped;
- for jobs, copies schedule, enabled, max runs and timeout while the plugin's job row is untouched (default cron, disabled, never run); run history stays on the old key;
- merges the old item's tags, visibility override and bookmarks into the new path;
- hides the old item (not registered, not listed, its job row disabled on every boot), so the two never both run.
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.
- today Changed · +46 lines · -100 tokens per session ba973cbb2b7b
- 11d ago Changed · +68 lines · +24 tokens per session 5ffd47c11872
- 1mo ago First seen · 103 lines · 76 tokens per session scan A de8a692b2be0
wick-plugins is a skill published in the GitHub repository yogasw/wick (3 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,569 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 2026-08-31.
Other skills, from other repositories
omh-rust
This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.
workflow-builder
Load before calling build-workflow. Default path for all single-workflow work: new one-off workflows, existing-workflow edits, verification repairs, and workflow-local data tables. Write or edit a workspace source file, run workflow-sdk validate via workspaceexecutecommand, then call build-workflow with filePath. When…
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…