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 agents/openagents-org/openagents/codebuddygit clone --depth 1 https://github.com/openagents-org/openagentsWhat 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 | $0.00000 | $0.01665 |
| Opus 5 | $0.00000 | $0.00833 |
| Sonnet 5 | $0.00000 | $0.00333 |
| Haiku 4.5 | $0.00000 | $0.00167 |
Grade A, and why
codebuddy 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeBuddy Code (and WorkBuddy)
CodeBuddy Code — Tencent's terminal agent, installed
as @tencent-ai/codebuddy-code — run as an OpenAgents agent.
This page exists mostly to answer one question: can WorkBuddy join a workspace? The short answer is yes, through this agent, with one real caveat.
WorkBuddy and CodeBuddy are the same engine
WorkBuddy is a desktop application. It has no command line, no documented local port, and no public API of its own — the only official programmable surface in the family is the Managed Agents API, which runs agents in Tencent's cloud sandbox and needs an enterprise key.
But the desktop app does not implement an agent. It spawns this CLI in a
sidecar (codebuddy --serve) and talks to it over local ACP:
WorkBuddy (Electron) → daemon app server → sidecar → codebuddy --serve → ACP → the window you see
The published CLI still carries the seams: CODEBUDDY_HOST=workbuddy-desktop,
WORKBUDDY_CONFIG_DIR, a workbuddy authentication platform, and
www.workbuddy.cn in its own product configuration. So driving the CLI directly
gets the same engine and the same account, with none of the fragility of
reverse-engineering a loopback port that only exists while a GUI is open.
The caveat: WorkBuddy's office abilities — decks, documents, spreadsheets — come from skills, plugins and MCP apps bundled inside the desktop application. They are not in the npm package. This agent is therefore the coding and general terminal agent, not the deck-and-spreadsheet one.
What the adapter does
codebuddy -p --output-format stream-json --verbose \
--append-system-prompt <workspace briefing> -y \
--disallowedTools … --mcp-config <config> [--resume <session>]
One process per user message; the prompt is piped over stdin. Workspace tools
(workspace_read_file, the shared browser, todos, …) arrive through the same
stdio MCP server the Claude adapter uses, so the briefing is the same one —
reused rather than forked.
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 First seen · 140 lines · 0 tokens per session scan A 5cc5ef151d24
codebuddy is an agent published in the GitHub repository openagents-org/openagents (4,029 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,665 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 2026-09-02.
Other agents, from other repositories
worker
General-purpose subagent with full capabilities, isolated context.
deep-review-claude
Independent deep technical review using Anthropic Claude model.
ai-readiness-reporter
Runs the AgentRC readiness assessment on the current repository and produces a self-contained, static HTML dashboard at reports/index.html. Explains every readiness pillar, the maturity level, and an actionable remediation plan, framed by AgentRC measure → generate → maintain loop. Use when asked to assess, audit…
Custom Agent Foundry
Expert at designing and creating VS Code custom agents with optimal configurations.
Agent Governance Reviewer
AI agent governance expert that reviews code for safety issues, missing governance controls, and helps implement policy enforcement, trust scoring, and audit trails in agent systems.
chat-agents
Build AI-powered chat interfaces with AIChatAgent and useAgentChat. Messages are automatically persisted to SQLite, streams resume on disconnect, and tool calls work across server and client.