setup-repo

setup-repo is a skill for Claude Code, Codex from firatcand/forge. It costs 31 tokens per session (484 once invoked), scanned A, original, MIT.

A repository setup workflow for GitHub projects. It creates or connects the repository, configures branch protection and environments, adds continuous-integration workflows, and prepares required secrets.

In plain words
What is it for?
Use it to bootstrap a project with a protected main branch, development and production environments, CI workflows, an environment-variable template, and an authentication secret.
Why use it?
It removes the repeated manual work of securing a new repository and configuring its automated checks and deployment settings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/firatcand/forge/setup-repo
Any agent
npx skills add firatcand/forge --skill setup-repo
Clone the repo
git clone --depth 1 https://github.com/firatcand/forge

Made for: Claude Code, Codex.

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 setup-repo

README.md
[![agentmods](https://agentmods.dev/badge/skills/firatcand/forge/setup-repo.svg)](https://agentmods.dev/skills/firatcand/forge/setup-repo)
Your own site
<a href="https://agentmods.dev/skills/firatcand/forge/setup-repo"><img src="https://agentmods.dev/badge/skills/firatcand/forge/setup-repo.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 484 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00484
Opus 5 $0.00015 $0.00242
Sonnet 5 $0.00006 $0.00097
Haiku 4.5 $0.00003 $0.00048

Measured 6d ago against content hash 2d1df729027e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

setup-repo 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 6d 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.

skills/setup-repo/SKILL.md · 60 lines

What it actually says

/setup-repo

Delegate to the devops-engineer subagent.

Preconditions

  • gh CLI installed and authenticated
  • spec/PRD.md exists
  • Run from inside the project directory

Steps (transparent — show each to user, don't hide)

  1. Verify gh CLI: gh auth status
  2. Create repo: gh repo create [name] --private --source=. --remote=origin
    • Or skip if origin already exists
  3. Initial commit: if no commits, commit current state to main
  4. Branch protection on main:
    • Require PR review (1)
    • Require test status check
    • No direct pushes
    • No force pushes
  5. GitHub Environments:
    • development (auto-deploy, no approval)
    • production (manual approval)
  6. Copy CI workflows from templates/github-workflows/ to .github/workflows/:
    • claude-issue.yml
    • claude-pr-review.yml
    • test.yml
    • claude-scheduled.yml
  7. Generate .env.example from SPEC.md env_vars list
  8. Setup Claude Code OAuth token:
    • Prompt user: claude setup-token
    • Read token from clipboard or stdin
    • Set as repo secret: gh secret set CLAUDE_CODE_OAUTH_TOKEN
  9. Commit and push: .github/, updated .env.example

Each step shown to user

Don't run all 9 steps silently. Print each:

[1/9] Verifying gh CLI authentication... ✓
[2/9] Creating repo firatcand/time-logger... ✓
[3/9] Initial commit on main... ✓
...

User can interrupt at any step.

Output

Repo URL + summary of what was configured. Branch protection rules summary. Workflow files list.

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. 6d ago First seen · 60 lines · 31 tokens per session scan A 2d1df729027e

Subscribe to this mod's changes

setup-repo is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 484 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 2026-08-30.