Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

Commencer

subagent

Étoiles3

Forks0

Mis à jour10 juillet 2026 à 17:34

Spawn a subagent to run a task. Use when you want to delegate work to a separate pi instance.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

gabrielfruet

gabrielfruet/.dotfiles

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Autres occupations informatiquesProfessions informatiques et mathématiques·SOC 15-1299

Explorateur de fichiers

2 fichiers

SKILL.md

readonly

name	subagent
description	Spawn a subagent to run a task. Use when you want to delegate work to a separate pi instance.

Subagent Skill

Spawn a subagent to run a task independently.

The script is at ~/.pi/agent/skills/subagent/subagent.sh

Usage

./subagent.sh "your prompt here"

Options

--model <model> - Model to use (use minimax by default, minimax/MiniMax-M3)
--thinking <level> - Thinking level: off, low, medium, high
--cwd <dir> - Working directory

Examples

./subagent.sh "List files in src/"
./subagent.sh "Find all TODO comments" --model minimax/MiniMax-M3

Long-running read-only research

For broad read-only searches (repo + git history + web), the subagent can take several minutes and block the main turn. Two patterns avoid the hang:

Background + watch: redirect output to a temp file and launch the subagent through the watch tool (process mode). The agent turn continues immediately and resumes when the subagent exits:
```
./subagent.sh "<prompt>" --cwd <dir> --thinking high > /tmp/sub.txt 2>&1
# wrap the line above in a `watch` (process mode) call
```
Verify, don't trust: on resume, read the temp file and verify any key claims against the actual files/history before acting on them.

If no output appears after a few minutes, cancel the watcher and continue with main-agent verification. Prefer narrow prompts; broad "search repo + history

web" prompts can hang or exceed useful runtime.

Plus depuis ce dépôt

même dépôt

pr-workflow

gabrielfruet/.dotfiles

Use when opening a PR and driving it to green CI — push the branch, write a high-level PR description, watch checks, fix failures, and keep looping until green; also use when an already-open PR gets new commits.

2026-07-163

task-memory

gabrielfruet/.dotfiles

Use when the user starts, resumes, switches, saves, or recalls a named task or ongoing work across sessions (e.g. "remember this", "continue X", "what was I doing on Y", "track this task").

2026-07-133

git-workflow

gabrielfruet/.dotfiles

Git commit workflow. Load when finishing any code-change task (after verification) to commit and push, or when explicitly staging/committing.

2026-07-133

lightly-repos-workflow

gabrielfruet/.dotfiles

Use when modifying or adding a transform, loss, model, method, package, task-model, config, docs page, or example in a Lightly AG repo (lightly-ssl or lightly-train) and you need repo-specific conventions.

2026-07-103

ltdetr-coco-recipe

gabrielfruet/.dotfiles

Use when configuring or replicating LT-DETR v2 (ltdetrv2-s/m/l/x) COCO benchmarks via the lightly-train wrapper — model alias map, global vs per-rank batch size, recipe invariants, ECDet config mapping, cluster pins, and common gotchas.

2026-07-103

task-memory

gabrielfruet/.dotfiles

Use when the user starts, resumes, switches, saves, or recalls a named task or ongoing work across sessions (e.g. "remember this", "continue X", "what was I doing on Y", "track this task").

2026-07-103

name	subagent
description	Spawn a subagent to run a task. Use when you want to delegate work to a separate pi instance.

Subagent Skill

Spawn a subagent to run a task independently.

The script is at ~/.pi/agent/skills/subagent/subagent.sh

Usage

./subagent.sh "your prompt here"

Options

--model <model> - Model to use (use minimax by default, minimax/MiniMax-M3)
--thinking <level> - Thinking level: off, low, medium, high
--cwd <dir> - Working directory

Examples

./subagent.sh "List files in src/"
./subagent.sh "Find all TODO comments" --model minimax/MiniMax-M3

Long-running read-only research

For broad read-only searches (repo + git history + web), the subagent can take several minutes and block the main turn. Two patterns avoid the hang:

Background + watch: redirect output to a temp file and launch the subagent through the watch tool (process mode). The agent turn continues immediately and resumes when the subagent exits:
```
./subagent.sh "<prompt>" --cwd <dir> --thinking high > /tmp/sub.txt 2>&1
# wrap the line above in a `watch` (process mode) call
```
Verify, don't trust: on resume, read the temp file and verify any key claims against the actual files/history before acting on them.

If no output appears after a few minutes, cancel the watcher and continue with main-agent verification. Prefer narrow prompts; broad "search repo + history

web" prompts can hang or exceed useful runtime.