workbuddy

workbuddy is an agent for coding agents from musistudio/claude-code-router. It costs 0 tokens per session (1,013 once invoked), scanned A, original, MIT.

A desktop coding agent named WorkBuddy that runs as an installed app. CCR Desktop can choose its provider, model, and allowed model list.

In plain words
What is it for?
Use it to create a WorkBuddy profile, restrict available models, set its app path, and launch it from CCR.
Why use it?
It centralizes WorkBuddy's launch settings and provides a fallback executable path when automatic detection fails.

Agent

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 agents/musistudio/claude-code-router/workbuddy
Clone the repo
git clone --depth 1 https://github.com/musistudio/claude-code-router

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 workbuddy

README.md
[![agentmods](https://agentmods.dev/badge/agents/musistudio/claude-code-router/workbuddy.svg)](https://agentmods.dev/agents/musistudio/claude-code-router/workbuddy)
Your own site
<a href="https://agentmods.dev/agents/musistudio/claude-code-router/workbuddy"><img src="https://agentmods.dev/badge/agents/musistudio/claude-code-router/workbuddy.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,013 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 $0.00000 $0.01013
Opus 5 $0.00000 $0.00507
Sonnet 5 $0.00000 $0.00203
Haiku 4.5 $0.00000 $0.00101

Measured 4d ago against content hash fec7fce01bb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workbuddy 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.

docs/src/content/docs/en/configuration/agents/workbuddy.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prerequisites

  1. CCR Desktop is running with at least one provider + model configured.
  2. WorkBuddy is installed on this machine. If CCR cannot detect it, set APP_PATH to the WorkBuddy executable.
  3. You are on Agent Config and click Add profile.

Create the profile

  1. On Agent Config, click Add profile and choose WorkBuddy.
  2. Enter a Config name (for example WorkBuddy - Work).
  3. Confirm Provider ID, Provider name, and WorkBuddy model.
  4. Optionally restrict Allowed model list. Leaving it empty makes every CCR model available in WorkBuddy.
  5. Set APP_PATH only if auto-detection does not find WorkBuddy.
  6. If you use AgentClaw, bind a Bot.
  7. Save, then open WorkBuddy from CCR with the play button.

Configuration reference

WorkBuddy is fixed to App only, so the entry mode is not editable. The fields you configure are:

Field How to set it Effect
Agent Choose WorkBuddy Creates a WorkBuddy App launch entry in CCR.
Config name Free text, e.g. WorkBuddy - Work Identifies the profile. Desktop commands use ccr-app "<name>" app; CLI commands use ccr "<name>" app.
Enabled Toggle on/off Disabled profiles are not applied and not offered as launch entries.
Effect scope Only opened from CCR / System default Keeps the profile limited to CCR launches, or makes it the system-default WorkBuddy profile. Only one enabled system-default WorkBuddy profile is allowed.
Provider ID Default claude-code-router Provider reference for this WorkBuddy profile.
Provider name Free text; default Claude Code Router Display name used by the generated profile.
WorkBuddy model A provider model or Fusion model Default model when WorkBuddy App opens.
Allowed model list Optional multi-select Controls which CCR models appear in WorkBuddy. Empty means all models.
APP_PATH Optional executable path Overrides app auto-detection. Use it when WorkBuddy is installed in a custom location.
Config file Path Used for the system-default WorkBuddy profile.
Environment variables Key/value rows Optional advanced overrides; leave empty for normal use.
Bot Select a saved Bot Binds an AgentClaw IM bot to the WorkBuddy App entry.

Read the full file on GitHub · 90 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 · 90 lines · 0 tokens per session scan A fec7fce01bb1

Subscribe to this mod's changes

workbuddy is an agent published in the GitHub repository musistudio/claude-code-router (37,021 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,013 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.