// Use when the user asks to run GNHF, says they are going to sleep or leaving and wants an agent-managed coding run, asks to supervise, steer, or review an active GNHF run, or gives feedback on GNHF results.
| name | gnhf |
| description | Use when the user asks to run GNHF, says they are going to sleep or leaving and wants an agent-managed coding run, asks to supervise, steer, or review an active GNHF run, or gives feedback on GNHF results. |
GNHF is an agent orchestrator: it repeatedly calls another coding agent until a natural-language stop condition is met. This skill teaches the host agent to prepare one durable run and, in Companion mode, steer or review it.
Core rule: the host agent orchestrates; GNHF executes. Do not manually implement inside the same scope while a GNHF worker is responsible for it unless the user explicitly changes the delegation.
In Companion mode, GNHF completion is not user acceptance. "Stop condition met" only means the worker stopped; the host still compares the result to the user's latest requirements and fresh verification.
Choose exactly one mode for the run.
Use when the task is bounded, verification is clear, and the user wants one configured run to proceed without steering.
Examples:
Use when the task is uncertain, exploratory, design-heavy, research-heavy, or likely to need course correction.
Default to Companion when the user asks to iterate until satisfied, requests multi-round work, provides review findings, asks for design/skill/documentation improvement, or asks for supervision.
Examples:
Check the installed CLI before relying on flags:
gnhf --help
Known shape:
gnhf \
--agent <claude|codex|rovodev|opencode|copilot|pi|acp:<target>> \
--max-iterations <n> \
--stop-when "<observable completion condition>" \
--prevent-sleep on \
"<worker prompt>"
If GNHF has no --model flag, put model requirements in the worker prompt or backend config. Do not invent unsupported flags.
Before launch:
git status --short
git branch --show-current
git log --oneline --max-count=5
Prompt skeleton:
Objective: <one concrete outcome>.
Use <agent/model requirement>. Work in this repo. Treat this as a long-running GNHF task.
Before coding, inspect the current repo, relevant docs, and recent commits. Preserve user changes. Do not make unrelated refactors.
After each meaningful slice, run relevant verification. If blocked, commit no fake success; leave notes with the blocker and evidence.
Stop only when: <observable completion condition>.
In Companion mode, evaluate after each iteration or meaningful output chunk:
| Signal | Action |
|---|---|
| Worker found a real blocker | Stop or relaunch with blocker-specific instructions |
| Good partial slice | Let it continue or tighten the next stop condition |
| Skipped requested research | Relaunch with research as explicit first deliverable |
| Worker changes unrelated files | Stop and review before continuing |
| Worker claims success without verification | Review immediately; relaunch only with evidence-based stop condition |
| Reviewer finds a blocking issue or user says not satisfactory | Relaunch with that finding as the sole bounded correction |
Steering prompt:
Continue from the current repo state. The previous run partially succeeded: <evidence>.
Do not redo completed work. Focus only on <bounded correction>.
The issue to fix now is <specific observed issue>. Verify with <commands/checks>.
Stop only when <observable condition>.
Use only in Companion mode, when the host is supervising quality or deciding whether to continue with another bounded run.
If the result needs follow-up, continue in Companion mode instead of presenting the run as complete. Do not merge unless explicitly authorized.
Use when the user provides findings such as "not preserved", "scope drift", "missing requirement", or "why did you stop".
Use when the user returns with "good morning", "how did last night's run go?", or similar after a GNHF run.
Do not ask what to review first. Reconstruct state:
git status --short
git branch --show-current
git log --oneline --decorate --max-count=20
pgrep -fl 'gnhf|claude|codex|copilot|opencode|rovodev' || true
Inspect likely GNHF branches, notes, logs, terminal sessions, and changed files. If a GNHF process is still running, report that first.
Report mode, agent, branch, status, changes, verification, stop-condition result, quality assessment, and recommended next action. Never summarize an overnight run from memory.
copilot: explicit GitHub Copilot CLI request or local Copilot config.codex: repo-aware code work or review-heavy tasks.claude: reasoning-heavy implementation or prose-heavy planning when configured.pi: explicit Pi request or local Pi configuration.opencode / rovodev: explicit request or repo-specific setup.acp:<target>: explicit ACP target request, or when the user wants to drive a custom ACP-compatible agent through GNHF.