vibe-delegate
Lets your agent delegate coding tasks to a specific tool. The main agent always retains final responsibility.
What it does
This tool delegates coding tasks to another tool called 'Mistral Vibe CLI'. You write the instructions and review the code it generates before accepting it.
When to use it
- ✓When you want an AI to write code and you want to review it before using it.
- ✓When the user specifically asks to use this coding tool.
- ✓For coding tasks that require careful review.
Example of what to ask your AI
“Ask the AI to write code to add a new feature to my website, but review the code before applying it.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
You write a 'brief' (detailed instructions) for the AI. The AI generates the code, and you review and approve the changes.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add sickn33/agentic-awesome-skills --skill vibe-delegateOr download just the file:
curl -L https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/plugins/agentic-awesome-skills-claude/skills/vibe-delegate/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Bundled upstream support
Supporting files are included at skill-relative paths. See UPSTREAM-NOTICE.md for their pinned sources, licenses, hashes, and import changes.
Vibe Delegate
When to Use
- You want to delegate a bounded coding task to a separate
vibeimplementer (Mistral Vibe) and then review its diff yourself. - The user explicitly asked for delegation to this implementer.
You are the orchestrator. Hand a bounded coding task to a separate implementer — the Mistral
Vibe CLI (vibe) — then review what it produced and land it yourself. You write the brief and own
the judgment; Vibe does the typing in its own session; 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
vibeCLI is not installed or authenticated.
Prerequisites (check once)
- Install
uv, then Mistral Vibe:uv tool install mistral-vibe
- Configure your API key with
vibe --setup, or setMISTRAL_API_KEYin the environment. - Confirm
vibe --versionsucceeds. - Work in, or point
--cdat, the target git repository.
The loop
Run these five steps per task. Steps 1, 4, and 5 require judgment; 2 and 3 are mechanical.
1. Write the brief
Vibe sees only the text you send plus what it can inspect in the workspace — no chat history or shared context. Include the goal, current state, what to change, what to leave untouched, the project's actual gates, and a report contract. Tell Vibe not to commit. Keep one task per brief. See references/writing-the-brief.md.
Default mode cannot approve most shell commands headlessly, so the orchestrator runs the gates. Ask
Vibe to run them only when the human explicitly authorized --full-access.
2. Dispatch
Use the bundled helper. It wraps Vibe's headless --prompt mode, captures the structured event
stream, and writes result.json. (<skill-dir> is the installed folder containing this SKILL.md.)
node "<skill-dir>/scripts/relay.mjs" --brief brief.txt --cd /path/to/repo
# limit turns for cost control: add --max-turns <n>
# indicative price threshold/token cap: add --max-price <usd> --max-tokens <n>
# planning/read-only: add --plan-only
# unrestricted shell and tools: add --full-access (explicit authorization required)
# resume the most recent session: add --resume-last (delta brief only)
# resume a specific session: add --session <id> (delta brief only)
# see all options: node .../relay.mjs --help
The child process'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.
3. Wait for completion
The helper blocks until Vibe 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 vibe exits 127 and writes status: "vibe_unavailable".
The watchdog writes status: "timeout"; terminating the relay on POSIX writes status: "aborted"
after stopping Vibe's process tree.
Trust process state and the working tree over a progress display. Completion means the process exited
and result.json exists.
4. Review — do not trust the self-report
Treat Vibe's final message and gate claims as claims:
- Re-run the project's gates yourself.
- Read the diff against the brief, starting with
touchedFiles. - Run relevant guard skills if installed.
- Round-trip migrations and grep for dangling references after removals or renames.
See references/review-and-land.md.
5. Land it
The implementer edits the working tree; the orchestrator commits. Commit only after the gates pass
and the diff holds. If rework is needed, send a delta brief with --resume-last or --session <id>,
then review again.
Autonomy and permissions
In --prompt mode the relay always sets the agent profile explicitly:
| Relay flag | What Vibe gets | Use when |
|---|---|---|
| (default) | --agent accept-edits |
Normal implementation — built-in file edits are approved |
…
FAQ
Do I need to install anything?
Yes, you need to install 'uv' and 'mistral-vibe', and set up your API key.
What is the 'brief'?
It's a set of detailed instructions you give to the AI, explaining what needs to be done, how it should be done, and what the success criteria are.
Can the AI make changes directly to my code?
Yes, but you review and approve the changes before they are finalized. You have the final control.
Details
Original description by the author
Delegate coding tasks to the Mistral Vibe CLI (`vibe`) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.
Popularity
- GitHub stars
- 48k
- Ranking position
- #4500
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
00-andruia-consultant
Helps your agent start or improve AI projects. It analyzes code, suggests tools, and creates action plans in Spanish.
sickn33/agentic-awesome-skills
007
Lets your agent perform security audits and threat modeling. It's useful for protecting projects against attacks and vulnerabilities.
sickn33/agentic-awesome-skills
10-andruia-skill-smith
Helps your agent create or improve AI tools. It defines how tools work, writes documentation, and validates the structure.
sickn33/agentic-awesome-skills
20-andruia-niche-intelligence
Lets your agent create a summary about a specific industry. It's useful for understanding the context, rules, usage patterns, and risks of a project, using reliable sources.
sickn33/agentic-awesome-skills
Similar skills
benchmark-optimization-loop
Has your agent improve something's speed in a measured way. It tests multiple versions and chooses the fastest one that still works correctly.
affaan-m/ECC
change-impact
Helps your agent analyze the impact of code changes before making them. It compares the planned vs. actual results afterward, covering paths, data, tests, and documentation. Useful for risky or system-wide changes.
affaan-m/ECC
click-path-audit
Lets your agent trace all user buttons and interactions to find bugs. It finds issues where functions seem to work alone but fail together. Useful when bugs persist even after debugging.
affaan-m/ECC