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-agentsnpx skills add yogasw/wick --skill wick-agentsgit 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-agents)<a href="https://agentmods.dev/skills/yogasw/wick/wick-agents"><img src="https://agentmods.dev/badge/skills/yogasw/wick/wick-agents.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 | $0.00075 | $0.01060 |
| Opus 5 | $0.00037 | $0.00530 |
| Sonnet 5 | $0.00015 | $0.00212 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
wick-agents 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 4d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using wick agents
An agent in wick is a CLI coding assistant (Claude Code, Codex, Gemini) or the in-process wick provider, run as a subprocess against a folder, reachable from several channels at once. Everything it does happens inside a session.
The mental model
Four things, in order of how often you touch them:
| What it is | |
|---|---|
| Session | One conversation. Auto-created on the first message in a Slack thread, a Telegram chat, or a fresh web conversation — never pre-allocated. |
| Project | One folder plus its defaults. The folder is the cwd the agent subprocess runs in. Several sessions can share one project. |
| Preset | Reusable agent instructions — one agent.md file. The built-in default preset is the fallback when a session has no project; it cannot be deleted, only edited. |
| Provider | Which CLI runs, and under which credentials. Two claude/... profiles with different tokens can coexist alongside codex and gemini. |
The folder is the agent's world. Whatever is in the project folder — files you put there, files the agent writes via Bash — is what it can see.
Projects: managed vs custom
- Managed — wick creates an empty folder under
~/.<app>/agents/projects/<id>/files/and deletes it when the project is deleted. - Custom — you point the project at an existing path anywhere on disk. Wick does not delete it on project delete.
Use custom when the agent should work on a real repo you already have; managed when you want a scratch space wick owns.
Channels
The same agent is reachable from Slack, Telegram, and the web UI. Each thread, chat, or web conversation becomes its own session, so context does not bleed between them.
The web UI is always on. Slack and Telegram need a bot token and access-control config under the Channels page, where you also set the default project new sessions land in.
The pool
A pool caps how many agent subprocesses run at once and FIFO-queues the rest. Idle sessions are killed and later resumed transparently, so a long-lived conversation does not hold a process hostage.
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.
- 4d ago First seen · 74 lines · 75 tokens per session scan A 358548abdec3
wick-agents is a skill published in the GitHub repository yogasw/wick (5 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 1,060 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
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
overleaf-sync
Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…
omh-code-review
This is a Hermes-native code-review workflow skill.
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.
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…