TeamFlow in Cline

1. Install

npx -y github:macleodlabs-ai/teamflow-plugin skills install --for cline

That writes:

• .cline/skills/<skill>/SKILL.md — the ten skills, in the only skills directory Cline reads
• .clinerules/teamflow.md — the reporting instruction, as a Cline rule
• ~/.cline/data/settings/cline_mcp_settings.json — the TeamFlow MCP server over streamable HTTP
• .clinerules/hooks/PostToolUse — the hook itself; it calls teamflow hook --for cline, prints nothing the tool could read as a denial, and exits 0 whatever happens

Add --scope user to install for every project on this machine, or --dry-run to see the file list without writing anything. Re-running it replaces TeamFlow's block and leaves the rest of each file alone.

2. The skills you get

The same ten the Claude Code plugin carries, generated from the same SKILL.md files. This tool loads them as skills, one directory each, with the name prefixed so they do not collide with anybody else’s in a shared directory.

Each one wraps a github:macleodlabs-ai/teamflow-plugin subcommand, so the skill and the shell command are the same thing. Inside Claude Code they are /teamflow:login, /teamflow:status and so on.

3. Sign in once

Cline surfaces the authorization when the server answers 401 and opens the browser from there. Cline 4.1.7 added both that and support for pre-registered OAuth clients; on anything older the server looks permanently unreachable.

4. By hand

The installer writes this for you. If you would rather paste it: ~/.cline/data/settings/cline_mcp_settings.json. The Cline CLI also reads ~/.cline/mcp.json. There is no project-level MCP file.

{
  "mcpServers": {
    "teamflow": {
      "type": "streamableHttp",
      "url": "https://codercat.io/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}

The UI writes the same entry: the MCP Servers icon -> Remote Servers -> name teamflow, the URL above, transport Streamable HTTP (recommended) -> Add Server.

Leave autoApprove empty until the team has watched a few reports go out. Adding macleodlabs_teamflow_call later stops Cline asking before each report, at the cost of nobody seeing what is sent.

Cline is the one skills-capable tool here that does not read the shared .agents/skills root, so it gets its own copy under .cline/skills. It also inverts the usual precedence: a global skill beats a project one of the same name, where every other tool has the project win. If you install at both scopes, ~/.cline/skills is the one Cline uses.

Cline also reads AGENTS.md at the root, and auto-detects .cursorrules and .windsurfrules if the repository already has one.

5. The stages to report

JIRA is the thirteenth: the ticket exists and nothing has started. Statuses are running, success, waiting, blocked, failed and idle. This is the same vocabulary the Claude Code plugin derives, so a ticket moved from here sits in the same column as one moved by Claude.

6. Without the agent

Anything that runs in a shell posts the same report with no model involved. A git hook, an npm script, a run configuration, a CI step:

npx -y github:macleodlabs-ai/teamflow-plugin report --issue DAEMON-142 --stage LOCAL_TEST \
  --status success --summary "42 tests, 0 failing"

Same envelope, same transport, same credential. Prefer it wherever the board has to be right whether or not an agent remembered. npx -y github:macleodlabs-ai/teamflow-plugin report --help lists every flag.

7. What this is not

Cline reports automatically through its own hooks: PostToolUse. Nothing to remember. Cline runs an executable named after the event rather than reading a config file, and hooks have to be switched on once in Settings before it will. Hooks have to be switched on once in Settings -> Features before Cline will run one.

The hooks see this tool's own calls and nothing else. A test run in another terminal, a merge from the web UI, a deploy from a pipeline: put npx -y github:macleodlabs-ai/teamflow-plugin report in the git hook or the script that already runs on every change, and those land on the board too.

8. What leaves your machine

TeamFlow is a delivery map for Jira, Linear and GitHub issues, run by MacleodLabs. Reports carry derived state only: a ticket key, a stage, a status, a short summary and evidence links. Prompts, diffs, source code, commands and logs are never sent and are rejected before they are charged.

• Every client
• llms.txt
• Capabilities
• The reporting contract, in full