cline-delegate — Claude Code skill: what it does, how to install
Delegates coding tasks to the Cline CLI agent in the background while keeping diff review and git commits under your control.
npx skills add amElnagdy/delegate-skills --skill cline-delegate -a claude-codeWhat cline-delegate does
This skill turns your environment into an orchestrator that hands implementation off to the separate Cline CLI agent. You formulate a self-contained task brief into a file, and the bundled scripts/relay.mjs relay streams it into cline --json, tracking progress and writing outputs to result.json.
The relay never commits code directly. Once Cline finishes, the orchestrator inspects touchedFiles, runs project validation gates, and reviews git diff before creating a git commit. For safe inspections, passing --plan forces read-only execution by rejecting automated tool approvals.
The skill will fail immediately unless cline is pre-installed and authenticated via cline auth or ANTHROPIC_API_KEY, with Node 18+ and git available.
What it helps with
- delegate implementation tasks to a background Cline CLI instance
- run read-only architecture passes using the
--planflag - review generated code diffs before landing commits in git
- queue standalone implementation tasks for an external coding agent
Example prompts for the agent
- Delegate this refactoring task to
clineusing a brief. - Run a read-only planning pass through
clinewith--plan. - Send this implementation brief to
clineand review the diff afterward.
How to install cline-delegate
1Skills CLI (Vercel)
npx skills add amElnagdy/delegate-skills --skill cline-delegate -a claude-code2Manually: put the files in place
~/.claude/skills/cline-delegate/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/cline-delegate/
1Skills CLI (Vercel)
npx skills add amElnagdy/delegate-skills --skill cline-delegate -a codex2Manually: put the files in place
.agents/skills/cline-delegate/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add amElnagdy/delegate-skills --skill cline-delegate -a cursor2Manually: put the files in place
.cursor/skills/cline-delegate/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install amElnagdy/delegate-skills cline-delegate2Manually: put the files in place
.github/skills/cline-delegate/SKILL.md1Skills CLI (Vercel)
npx skills add amElnagdy/delegate-skills --skill cline-delegate -a gemini-cli2Platform CLI
gemini skills install https://github.com/amElnagdy/delegate-skills --path skills/cline-delegateManually: put the files in place
.devin/skills/cline-delegate/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add amElnagdy/delegate-skills --skill cline-delegate -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about cline-delegate
How do I install cline-delegate in Claude Code?
Run npx skills add amElnagdy/delegate-skills --skill cline-delegate -a claude-code.
What does cline-delegate do?
It sends tasks to the Cline CLI in the background, writes run artifacts to result.json, and lets you verify and commit the final diff.
What prerequisites are required for cline-delegate?
You need Node 18+, git, and the cline CLI installed and authenticated with cline auth or an ANTHROPIC_API_KEY.
Source text
SKILL.md · MIT
--- name: cline-delegate description: >- Delegate a coding task to the Cline coding agent CLI (`cline`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Cline - phrasings like "have Cline implement X", "delegate this to cline", "run it through Cline", or "use cline to implement/fix/refactor" - or wants to run a queue of coding tasks through Cline while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating. license: MIT compatibility: Requires the `cline` CLI installed and authenticated with `cline auth`, Node 18+, and git. The orchestrator must be able to run shell commands and read files. metadata: version: 0.5.0 --- # Cline Delegate You are the **orchestrator**. Delegate a bounded coding task to a separate **implementer** - the Cline coding agent CLI - then review what it produced and land it yourself. You write the brief and own the judgment; the implementer makes changes in its own session in a clean working tree; you verify and commit. The loop needs only a shell command and file access, so any comparable orchestrator can drive it. ## When NOT to use this - The task is small enough to do inline; delegation overhead is not worth it. - The `cline` CLI is not installed or authenticated. - You require the relay to configure a sandbox. Cline exposes sandbox controls, but this relay leaves them to the CLI environment; use `--plan` when the run must be read-only. ## Prerequisites (check once) 1. Install `cline` (npm or bundled binary; the relay probes `cline --version`). 2. Authenticate: run `cline auth` (interactive sign-in), or configure `ANTHROPIC_API_KEY` / an OpenAI-compatible base URL. 3. Confirm `cline --version` succeeds. 4. Work in, or point `--cd` at, the target git repository. ## Choose the model (optional) Cline picks a default model. To choose another, pass the separate `--model <id>` or `--provider <name>` (e.g. `anthropic`, `openai-native`, `openrouter`). The relay accepts letters, digits, and `. _ : / -` only (the value reaches a shell on Windows). ## The loop Run these five steps per task. Steps 1, 4, and 5 require judgment; 2 and 3 are mechanical. ### 1. Write a brief Cline sees only the text you send. It cannot read your conversation: the brief must stand alone with the goal, current state, what to change, what to leave untouched, the project's **real** gates, and a report contract. Keep each brief to a single task. Write it to a file and pass it as the relay's `--brief`. See [references/writing-the-brief.md](references/writing-the-brief.md). ### 2. Dispatch For **Codex orchestration of background work**, install and configure the separate **codex-background** support utility first. If its MCP tools or registry are missing, stop and report the setup requirement; do not silently fall back to model-driven polling. Then invoke its registered `delegate_run` MCP tool once in place of the shell example below. Follow that skill for structured common arguments, unchanged provider flags and reattachment by runId. Keep the request pending until completion, then continue this skill's review and landing steps. Other orchestrators keep the shell workflow below. Use the bundled relay. It runs `cline --json -v`, streams the brief on stdin behind a fixed positional instruction, captures the JSON event stream, and writes `result.json`. ```bash node "<skill-dir>/scripts/relay.mjs" --brief brief.txt --cd /path/to/repo # choose a model / provider: add --model <id> --provider <name> # read-only planning pass: add --plan (forces --auto-approve false) # deny approval-required tools: add --auto-approve false # hard time limit (watchdog): add --timeout 2h (the 30m default suits brief runs; most implementation briefs should be 1-2h) # see all options: node .../relay.mjs --help ``` The child's cwd pins the workspace. The relay writes artifacts under the system temp dir by default and never commits. See [references/dispatch-and-poll.md](references/dispatch-and-poll.md). ### 3. Wait for completion Codex using codex-background keeps the original MCP request pending: no model-driven sleep, status or log polling. Use `delegate_wait` only to reattach after an interrupted request. The relay blocks until cline finishes. Run it with the orchestrator's background-command facility, or background it in the shell and poll for `result.json`. A pre-run usage error exits 2 and writes no result; a missing `cline` exits 127 and writes `status: "cline_unavailable"`. Completion means the process exited and `result.json` exists - trust process state and the working tree, not the progress display. Cline's final message is the `finalMessage` field of `result.json`. ### 4. Review - do not trust the self-report - Re-run the project's gates yourself. - Read the diff against the brief, starting with `touchedFiles`. - Run relevant guard skills if installed. See [references/review-and-land.md](references/review-and-land.md). ### 5. Land it If the work is good, commit it. The relay never commits - the diff and `result.json` are the record; run `git status` and `git diff` first to confirm exactly what changed. If the group has a PR flow, make the commit and push a branch; let human review happen. If the diff is wrong or incomplete, re-dispatch a corrected brief in a fresh run and review again. ## Autonomy and permissions The relay explicitly passes Cline's `--auto-approve`, defaulting to `true` in act mode. Cline plan mode can request a switch to act mode, so `--plan` forces `--auto-approve false`; the relay rejects `--plan --auto-approve true`. That pair is the read-only gate. Cline also exposes sandbox through `--data-dir` / `CLINE_SANDBOX`, but the relay does not configure or override it. Plan-first for anything risky, then review the plan before a separate act-mode dispatch. Malformed or malicious briefs remain dangerous in act mode because commands run as the current user. ## Authorization model Delegation is something the human opts into. Once briefed, cline works as a tool you approved use of. The boundary is: **do not accept conclusions from the self-report**; verify everything on disk. For anything touching credentials, production data, or irreversible operations, stop and ask the human first instead of encoding it in a brief. ## References - [references/writing-the-brief.md](references/writing-the-brief.md) - structure, scope, gates, brief delivery. - [references/dispatch-and-poll.md](references/dispatch-and-poll.md) - flags, artifacts, `result.json`, and failure recovery. - [references/review-and-land.md](references/review-and-land.md) - what to verify before calling the diff done, at the end of a run. - [references/multi-task-queues.md](references/multi-task-queues.md) - sequential queues, constraint carry-forward, progress tracking, and the final coherence pass.
© amElnagdy · MIT · amElnagdy/delegate-skills