egapro: Skill for Claude Code

.claude/skills/open/SKILL.md

open is a skill for Claude Code from SocialGouv/egapro. It costs 34 tokens per session (665 once invoked), scanned A, original, Apache-2.0.

A command that recreates a local worktree for a GitHub pull request. A worktree is a separate checkout of the repository, allowing the proposed changes to be tested without changing the main checkout.

In plain words
What is it for?
It accepts a pull-request number, restores or reuses the matching worktree, runs setup when needed, and reports paths and local service URLs for testing.
Why use it?
A worktree may have been removed after another agent finished implementing a pull request. Recreating it lets a developer run the code locally before merging.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents.

This is SocialGouv/egapro's own configuration. It tells Claude Code how to work on egapro 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 egapro configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/orchestration/open_worktree.sh "$PR".

Reuse

Borrowing it

Nothing to install: this file belongs to SocialGouv/egapro. 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/SocialGouv/egapro/alpha/.claude/skills/open/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/SocialGouv/egapro

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 open

README.md
[![agentmods](https://agentmods.dev/badge/skills/socialgouv/egapro/open.svg)](https://agentmods.dev/skills/socialgouv/egapro/open)
Your own site
<a href="https://agentmods.dev/skills/socialgouv/egapro/open"><img src="https://agentmods.dev/badge/skills/socialgouv/egapro/open.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 665 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 $0.00034 $0.00665
Opus 5 $0.00017 $0.00332
Sonnet 5 $0.00007 $0.00133
Haiku 4.5 $0.00003 $0.00067

Measured yesterday against content hash 954529e07b10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

open 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 yesterday.

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.

.claude/skills/open/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/open

Recreate the egapro worktree associated with a PR — typically one that was auto-cleaned by /implement after the sub-agent returned validated. Use this to test the PR's code locally : run the dev server, exercise the feature, debug issues before merging.

Arguments

$ARGUMENTS — PR number (#3341, 3341). Required.


Ton rôle

Tu es un thin wrapper. Toute la logique est dans scripts/orchestration/open_worktree.sh. Tu dois :

  1. Valider que l'argument est un nombre de PR
  2. Lancer le script
  3. Relayer son output à l'utilisateur (path + URLs)
PR=$ARGUMENTS  # strip leading #
PR=${PR#\#}

if ! [[ "$PR" =~ ^[0-9]+$ ]]; then
    echo "ERROR: argument must be a PR number"
    exit 1
fi

bash scripts/orchestration/open_worktree.sh "$PR"

Le script :

  • Résout la branche head + le ticket linked + l'epic parent
  • Choisit le premier slot libre dans [0, EPIC_MAX_PARALLEL[
  • Recrée le worktree (idempotent : réutilise s'il existe)
  • Lance setup-worktree.sh si .env.local est manquant (pnpm install + docker stack + migrations)
  • Affiche le path + les URLs (dev server, mailpit, minio, postgres)

Cas d'usage typiques

  • Tester une PR ouverte avant de la merger : /open 3341 → worktree recréé, dev server prêt sur http://localhost:3001 (ou autre selon le slot)
  • Reprendre un debug sur une PR rejetée par CI : /open <PR> puis cd <path> et bidouiller
  • Reproduire un bug sur le code d'une PR mergée mais qui pose problème en preprod : /open <PR> même après merge — la branche reste sur le remote

Limitations

  • Si tous les slots [0, EPIC_MAX_PARALLEL[ sont occupés (par d'autres worktrees actifs), le script retourne une erreur. Libérer un slot via git worktree remove ../egapro-epic*-tXXX ou augmenter EPIC_MAX_PARALLEL.
  • Si la PR a été créée hors de la pipeline /implement (pas de ticket lié, pas d'epic parent), le script échoue. Cas limite — créer le worktree à la main dans ce cas.

Read the full file on GitHub · 65 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. yesterday First seen · 65 lines · 34 tokens per session scan A 954529e07b10

Subscribe to this mod's changes

open is a skill published in the GitHub repository SocialGouv/egapro (12 stars, last pushed 3d ago), licensed Apache-2.0. It adds 34 tokens to every session and 665 once invoked, about $0.0002 per session on Opus 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 2026-09-04.

Related

Other skills, from other repositories

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

codex-autoresearch

Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…

leo-lilinxiao/codex-autoresearch · 80 tokens

changelog-composer

Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".

Mathews-Tom/armory · 67 tokens