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.
npx skills add gabrieldabbah/genesis --skill repo-hardeninggit clone --depth 1 https://github.com/gabrieldabbah/genesisWrote 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.
[](https://agentmods.dev/skills/gabrieldabbah/genesis/repo-hardening)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- 12d ago First seen · 102 lines · 110 tokens per session scan A f3e425300f25
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.
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.
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.
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.
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).
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.
ops-ship
OPS on-demand: This skill should be used when the user asks to "ship ops plugin", "merge all PRs and…