repo-hardening

repo-hardening is a skill for Claude Code from gabrieldabbah/genesis. It costs 110 tokens per session (1,337 once invoked), scanned A, original, MIT.

A repository setup for GitHub projects that adds automated checks, dependency updates, and rules protecting the main branch. It makes passing the required check a condition for merging code.

In plain words
What is it for?
Use it to configure continuous integration, automatic dependency update pull requests, branch protection, and a required CI check on a hosted repository.
Why use it?
It reduces the chance that broken code reaches the main branch or that outdated dependencies remain unnoticed. It also makes the merge rules explicit instead of relying on manual care.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Part of the genesis plugin — 10 skills, 1 hook shipped together

Good fit Use it to configure continuous integration, automatic dependency update pull requests, branch protection, and a required CI check on a hosted repository.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gabrieldabbah/genesis/repo-hardening
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.

Any agent
npx skills add gabrieldabbah/genesis --skill repo-hardening
Clone the repo
git clone --depth 1 https://github.com/gabrieldabbah/genesis

Made for: Claude Code.

Or install genesis, the plugin that ships this one along with the rest of its 10 skills, 1 hook.

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 repo-hardening

README.md
[![agentmods](https://agentmods.dev/badge/skills/gabrieldabbah/genesis/repo-hardening/github.svg)](https://agentmods.dev/skills/gabrieldabbah/genesis/repo-hardening)
Your own site
<a href="https://agentmods.dev/skills/gabrieldabbah/genesis/repo-hardening"><img src="https://agentmods.dev/badge/skills/gabrieldabbah/genesis/repo-hardening/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 repo-hardening

Your own site · 80×15
<a href="https://agentmods.dev/skills/gabrieldabbah/genesis/repo-hardening"><img src="https://agentmods.dev/badge/skills/gabrieldabbah/genesis/repo-hardening.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,337 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 $0.00110 $0.01337
Opus 5 $0.00055 $0.00668
Sonnet 5 $0.00022 $0.00267
Haiku 4.5 $0.00011 $0.00134

Measured 12d ago against content hash f3e425300f25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

repo-hardening 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 12d 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/repo-hardening/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo hardening — make broken code unmergeable

Four things, in this order. The order is not cosmetic: step 4 depends on the check from step 2 having actually run, and doing it earlier fails with a confusing error.

Assumes a repository hosted on GitHub with a default branch that deploys or releases. Adapt the mechanics for another host; the four properties are the same everywhere.

Every step here changes settings on a hosted repository the user owns. Propose the set, then apply on their go-ahead. Nothing in this skill is urgent enough to justify surprising someone with a changed merge policy.

1. Automated dependency updates

Turn on the host's dependency alerts and automatic security updates, and commit a config that also opens routine (non-security) update PRs on a schedule. Group them — a weekly batch is reviewable, thirty individual PRs are not. A scaffolded project already has that config at .github/dependabot.yml; check its ecosystem matches the stack, and that a project with several manifests has a block per directory.

The alerts are a repository setting and the config is a file: turning on one without the other looks the same from the outside as doing both, and neither half announces the absence of the other.

Why it earns its place: a dependency advisory is the one class of problem that arrives on someone else's schedule rather than yours.

2. Continuous integration

Add a workflow that runs the project's own gate on every pull request and on pushes to the default branch. A scaffolded project already has one at .github/workflows/ci.yml; a project that does not gets it written now, with the same properties.

The run command comes from the project, not from a guess. Read CLAUDE.md §Commands, then the manifest's scripts. Use what is actually there — the test command if the project has tests, otherwise the build, which at least catches a type or compile error. A CI job that runs nothing is worse than none, because it goes green and implies something was checked.

Read the full file on GitHub · 102 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. 12d ago First seen · 102 lines · 110 tokens per session scan A f3e425300f25

Subscribe to this mod's changes

repo-hardening is a skill published in the GitHub repository gabrieldabbah/genesis (4 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 1,337 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

pr-watch

Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.

SethGammon/Citadel · 46 tokens

deploy-steward

Mainline deploy steward. Consumes ready PRs, owns a lease on mainline landing, refreshes PR state, updates stale branches, waits for CI and deploy gates, merges or queues one candidate at a time, and opens repair tasks for failures.

SethGammon/Citadel · 56 tokens

merge-review

Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.

SethGammon/Citadel · 40 tokens

push-ci

Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI. Use when: user says 'push', 'push and watch CI', 'ship it', 'push-ci'. Not for: committing (use /smart-commit), creating PRs (use /create-pr), merging (use /merge-prep).

sd0xdev/sd0x-harness · 82 tokens

cloudflare-workers-ci-cd

Complete CI/CD guide for Cloudflare Workers using GitHub Actions and GitLab CI. Use for automated testing, deployment pipelines, preview environments, secrets management, or encountering deployment failures, workflow errors, environment configuration issues.

secondsky/claude-skills · 50 tokens

ops-ship

OPS on-demand: This skill should be used when the user asks to "ship ops plugin", "merge all PRs and…

Lifecycle-Innovations-Limited/claude-ops · 30 tokens