blog
Write release blog posts for Chorus — problem-first narrative, bilingual (zh/en), following the project's editorial style.
How to install, configure, and use the `chorus` CLI — install it, manage agents with `chorus agents` (add/remove/list), the connection environment variables, and MCP operations via `chorus mcp`. A concise shared reference for any flow that drives Chorus from the shell.
$ npx -y skills add Chorus-AIDLC/Chorus --skill chorus-cli --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/chorus-cliContext preview
The summary Claude sees to decide when to auto-load this skill.
How to install, configure, and use the `chorus` CLI — install it, manage agents with `chorus agents` (add/remove/list), the connection environment variables, and MCP operations via `chorus mcp`. A concise shared reference for any flow that drives Chorus from the shell.
name: chorus-cli description: How to install, configure, and use the `chorus` CLI — install it, manage agents with `chorus agents` (add/remove/list), the connection environment variables, and MCP operations via `chorus mcp`. A concise shared reference for any flow that drives Chorus from the shell. license: AGPL-3.0 metadata: author: chorus version: "0.18.0" category: project-management mcp_server: chorus
`chorus` (published as `@chorus-aidlc/chorus`) is the one command that configures this machine's coding agents for Chorus and talks to the Chorus MCP endpoint from the shell. This is a concise reference — run `chorus --help` and `chorus <command> --help` for the full flag surface.
npm install -g @chorus-aidlc/chorus # unpinned — always installs the latest chorus --version # must be >= 0.17.0 (provides `chorus agents` + `chorus mcp`)
Agent configuration lives in `~/.chorus/daemon.json`; `chorus agents` is the CRUD group:
The API key is never printed; the agent named by `CHORUS_AGENT_PROFILE` is marked.
— detect installed coding agents, install each one's Chorus plugin, and seed credentials (this is the former `chorus init`). Idempotent; safe to re-run. `--help` lists every flag.
(matched by UUID or name; an ambiguous name → use the UUID).
configured agent's binary in the FOREGROUND with its Chorus connection injected into the child only (`CHORUS_URL` / `CHORUS_API_KEY` / `CHORUS_AGENT_PROFILE`; nothing is exported to the parent shell, and the key is never printed). Agent selection: single agent by default; else `--name`, else `CHORUS_AGENT_PROFILE`; ambiguous/none → error. Backend defaults to the agent's stored `agentType`, overridable with `--type`. Everything after `--` is passed to the agent **verbatim** (never inspected). Type → binary: `claude-code`/`claude`→`claude`, `codex`→`codex`, `kiro`→`kiro-cli`, `pi`→`pi`, `opencode`→`opencode`, `openclaw`→`openclaw`, `dsh`→`dsh-jsonrpc-agent`. Agents added as opencode/openclaw/dsh are stored as `offline` → pass `--type` explicitly to launch them.
resolves that agent's key from `~/.chorus/daemon.json`, so you need not export `CHORUS_API_KEY` for the CLI path. Daemon-woken sessions receive it automatically. (dsh scrubs credential-shaped env from tool subprocesses; the dsh doc-mirror wrapper also reads `CHORUS_AGENT_PROFILE` / credentials from `$DSH_HOME/.env`.)
Call any Chorus MCP tool from the shell — a byte-exact, token-free path for large content:
`--arg-file content=<file>` streams a file's raw bytes into the JSON `content` string (no re-typing through the model). Identity resolves from `--agent` → `CHORUS_AGENT_PROFILE` → `CHORUS_URL`+`CHORUS_API_KEY` → a single configured agent.
Requires `chorus >= 0.17.0` (the `chorus mcp` subcommand). See `chorus mcp --help`.
The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)
Repo: Chorus-AIDLC/Chorus
Write release blog posts for Chorus — problem-first narrative, bilingual (zh/en), following the project's editorial style.
Use when manually verifying a Chorus frontend change in a real browser — finding local login credentials, driving the running dev server with the Playwright…
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through…
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal…