vibe-delegate
Delegate coding tasks to the Mistral Vibe CLI (`vibe`) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 12
- Forks
- 3
01 前言 Front Matter
- name
- vibe-delegate
- risk
- critical
- source
- https://github.com/amElnagdy/delegate-skills
- license
- MIT
- category
- agent-orchestration
- metadata
- { "version": "0.5.0" }
- date_added
- 2026-08-26
- description
- Delegate coding tasks to the Mistral Vibe CLI (`vibe`) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.
- source_repo
- amElnagdy/delegate-skills
- source_type
- community
- license_source
- https://github.com/amElnagdy/delegate-skills/blob/master/LICENSE
02 资源文件 7
- 参考文档references/dispatch-and-poll.md8.0 KB
- 参考文档references/multi-task-queues.md2.3 KB
- 参考文档references/review-and-land.md4.0 KB
- 参考文档references/writing-the-brief.md5.5 KB
- 脚本scripts/relay.mjs27.9 KB
- 参考文档UPSTREAM-LICENSE.txt1.1 KB
- 参考文档UPSTREAM-NOTICE.md1.3 KB
03 SKILL.md 正文
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.
Run boundaries
Use an isolated task worktree and authorized provider/model/data scope. Cwd and prompt constraints are not filesystem confinement. Profiles, resumed sessions and fleet settings must be inspected; resume-last can select the wrong session, so verify identity before continuation. Run artifacts contain private briefs/output; use fresh private paths and redact before sharing. Completion status certifies child exit only, never task correctness. Commit/push/merge stay within the actual user and repository authorization.
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 |
--plan-only |
--agent plan |
Read-only review, exploration, or planning |
--full-access |
--agent auto-approve |
Explicitly authorized runs that need arbitrary shell/tools |
Default mode lets Vibe edit files inside the target worktree. Approval-gated shell commands,
including most project gates, are denied headlessly; the orchestrator runs the gates.
--full-access disables Vibe's tool approvals and permits arbitrary shell/tool execution under the
user account; use it only with explicit human authorization. Always inspect touchedFiles and the
diff after a run.
--trust is always passed to prevent interactive directory-trust prompts in headless runs. It is
not a sandbox and does not grant tool permissions.
Authorization model
Delegation is something the human opts into. Once they have ("run this queue", "proceed"), committing verified, gate-passing work is the agreed contract. Two limits remain: surface, don't absorb (report Vibe's design decisions, defensible-but-unasked turns, and non-blocking nitpicks) and stop for scope changes (if correct completion needs going beyond the brief, ask instead of expanding the mandate). See references/review-and-land.md.
References
- references/writing-the-brief.md — structure, report contract, real gates, argv delivery, and delta briefs.
- references/dispatch-and-poll.md — flags, artifacts,
result.json, polling, and failure recovery. - references/review-and-land.md — review checklist, commit boundary, and rework through Vibe sessions.
- references/multi-task-queues.md — sequential queues, constraint carry-forward, progress tracking, and the final coherence pass.
Limitations
- Runtime helper
scripts/relay.mjsis bundled from the revision recorded inUPSTREAM-NOTICE.md. Requires the corresponding installed and authenticated CLI, Node 18+, and git. - Relay never commits — it only returns structured result JSON; you review and land the commit.
Adapted from amElnagdy/delegate-skills (MIT) — runtime and references pinned in UPSTREAM-NOTICE.md.
04 同仓库更多 Skills
web-access
Use Treg for public web or platform data only when existing search, browser and connected tools cannot cover the task, with explicit cost and data boundaries.
treg
Use the Treg CLI or MCP catalog to discover, price and call authorized external tools with team-scoped credentials and a user-approved budget.
recruit
Turn a job description into an evidence-linked candidate shortlist through Treg, with job-related ranking and optional authorized business contact enrichment.
rea-growth
Analyze a company’s public growth and content through Treg, distinguish observations from hypotheses, and produce an evidence-linked playbook within an approved budget.
make-ugc
Create original AI UGC-style product videos through Treg: research hooks, approve a licensed presenter and voice, generate clips, add captions and report costs.
lead-signals
Find and qualify public buying signals through Treg, rank fitting business accounts and optionally enrich authorized business contact information.