wick-agents

wick-agents is a skill for Claude Code, Codex from yogasw/wick. It costs 75 tokens per session (1,060 once invoked), scanned A, original, MIT.

A guide to running coding agents in folders and reaching them through conversations such as Slack, Telegram, or the web. It explains sessions, projects, reusable instruction presets, providers, and the queue of running agents.

In plain words
What is it for?
Use it to create and manage agent sessions and projects, choose providers and presets, connect channels, understand the agent queue, and locate saved agent state.
Why use it?
It gives a clear model for where an agent works, which command-line assistant and credentials it uses, and how separate conversations share project settings.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/yogasw/wick/wick-agents
Any agent
npx skills add yogasw/wick --skill wick-agents
Clone the repo
git clone --depth 1 https://github.com/yogasw/wick

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for wick-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/yogasw/wick/wick-agents.svg)](https://agentmods.dev/skills/yogasw/wick/wick-agents)
Your own site
<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>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,060 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash 358548abdec3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

internal/agents/skillsync/builtin/wick-agents/SKILL.md · 74 lines

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.

Read the full file on GitHub · 74 lines

Changes

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.

  1. 4d ago First seen · 74 lines · 75 tokens per session scan A 358548abdec3

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories