base: Skill for Claude Code

.ai/agents/createur-agent/skills/competences/deleguer-a-plusieurs-branches/SKILL.md

deleguer-a-plusieurs-branches is a skill for Claude Code from ai-swiss/base. It costs 24 tokens per session (1,070 once invoked), scanned A, original, Apache-2.0.

A workflow for deciding when work can be split safely across several Git branches or agents and how to review the combined result. A branch is a separate line of code changes that can later be merged.

In plain words
What is it for?
Use it to check whether tasks are truly independent, define shared outputs and allowed files, and perform one review after merging.
Why use it?
It prevents parallel work from creating dependencies, conflicting edits, or a merge that no one reviews as a whole.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is ai-swiss/base's own configuration. It tells Claude Code how to work on base itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything base configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ai-swiss/base. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ai-swiss/base/main/.ai/agents/createur-agent/skills/competences/deleguer-a-plusieurs-branches/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ai-swiss/base

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for deleguer-a-plusieurs-branches

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-swiss/base/deleguer-a-plusieurs-branches/github.svg)](https://agentmods.dev/skills/ai-swiss/base/deleguer-a-plusieurs-branches)
Your own site
<a href="https://agentmods.dev/skills/ai-swiss/base/deleguer-a-plusieurs-branches"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/deleguer-a-plusieurs-branches/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for deleguer-a-plusieurs-branches

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai-swiss/base/deleguer-a-plusieurs-branches"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/deleguer-a-plusieurs-branches.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,070 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.01070
Opus 5.5 $0.00010 $0.00428
Sonnet 5.5 $0.00005 $0.00214
Haiku 4.5 $0.00002 $0.00107

Measured 1mo ago against content hash b01a21ab64e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deleguer-a-plusieurs-branches scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.ai/agents/createur-agent/skills/competences/deleguer-a-plusieurs-branches/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Déléguer à plusieurs branches

Un assistant peut répartir un travail entre plusieurs branches: plusieurs lectures menées de front, plusieurs sous-tâches, plusieurs agents. Cette compétence décrit ce qui rend une telle répartition sûre. Découper n'améliore rien en soi; ce sont les cinq conditions ci-dessous qui rendent le découpage tenable.

Exemple suivi d'un bout à l'autre: un atelier doit préparer trois devis pour trois clients, à partir d'un même barème de prix.

1. Rester ensemble par défaut

Le travail reste sur une seule branche tant qu'une raison de le découper ne s'impose pas. On découpe seulement si les parties sont indépendantes par construction, c'est-à-dire si aucune branche n'a besoin d'un résultat produit par une autre. Quand cette indépendance demande une démonstration, elle n'est pas acquise.

Les trois devis s'adressent à trois clients différents et se chiffrent sur un barème figé. Aucun devis n'a besoin du total d'un autre. La condition est remplie.

2. Le contrat partagé est un fichier

Le contrat dit ce que chaque branche doit produire, dans quelle forme, à partir de quelles références, dans quels chemins elle peut écrire et quels contrôles elle doit réussir. Il existe comme fichier avant que la première branche démarre, et chaque branche le lit en premier. Un contrat gardé dans la conversation se perd au premier embranchement: une branche ne voit que ce qui lui a été transmis.

Le contrat tient ici dans un fichier unique: le barème à utiliser, le gabarit de devis, la règle d'arrondi, la devise. Les trois branches partent du même texte.

3. Périmètre d'écriture et retour déclarés

Avant de démarrer, une branche annonce les fichiers qu'elle a le droit d'écrire, puis ce qu'elle rend et sous quelle forme. Deux branches autorisées à écrire le même fichier forment une seule branche.

Chaque retour adopte la même forme:

  • état ready_for_join ou blocked;
  • résultats produits et chemins modifiés;
  • contrôles exécutés et résultats obtenus;
  • sources utilisées;
  • incertitudes restantes et décisions demandées.

Read the full file on GitHub · 97 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 97 lines · 24 tokens per session scan A b01a21ab64e3

Subscribe to this mod's changes

deleguer-a-plusieurs-branches is a skill published in the GitHub repository ai-swiss/base (65 stars, last pushed 8d ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,070 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.

Related

deleguer-a-plusieurs-branches compared with skills from other repositories

deleguer-a-plusieurs-branches next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
deleguer-a-plusieurs-branchesai-swiss/baseSkill658d agoApache-2.0A24Claude Code
rea-changelog-updatemorluto/reaSkill435kyesterdayMITA33Claude Code
repo-hygieneQwenLM/qwen-codeSkill29kyesterdayApache-2.0A48Claude Code, Codex
gh-skillcli/cliSkill47kyesterdayMITA41Claude Code, Codex
atmos-hookscloudposse/atmosSkill1.4kyesterdayApache-2.0A46Claude Code
conventional-committermio-sh/termioSkill7854d agoMITA47Claude Code, Codex
mergeautomagik-dev/genieSkill351yesterdayMITA32Codex