agentleFS
cobusgreylingcobusgreyling/grok-bot-templates/skills/harden-repo/SKILL.md

harden-repo

Skill14 starsChanged 3 months agoMITView on GitHub

Paste this into Grok Bot after a successful run: Save the process we just used as a skill called “Harden Repo”. A useful skill states the six fields from Skills and routines. A repository needs a security and hygiene review that recommends issues and PRs without touching main or branch protection. Each finding cites a setting, file, or workflow. No invented scanners. Main is untouched. Branch protection is unchanged. Hygiene pack: Findings, Recommended issues, Recommended PRs, Out of scope, Action…

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Read default branch, protection summary, CODEOWNERS, secret scanning, Dependabot, and workflow permissions as the connector exposes them.

    line 22
  2. Distinctive:

    Never push to main. Never change branch protection, required reviewers, or org policies.

    line 25
  3. Distinctive:

    Do not push, merge, publish, or change production.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Harden Repo

Paste this into Grok Bot after a successful run:

Save the process we just used as a skill called “Harden Repo”.

A useful skill states the six fields from Skills and routines.

1. When to use it

A repository needs a security and hygiene review that recommends issues and PRs without touching main or branch protection.

2. Required inputs and access

  • GitHub repository
  • Org or repo settings the connector can read
  • Optional prior harden notes in /workspace/repo-hardener/

3. Sequence of work

  1. Read default branch, protection summary, CODEOWNERS, secret scanning, Dependabot, and workflow permissions as the connector exposes them.
  2. List concrete gaps with paths or setting names. Separate facts (what is off) from inferences (what an attacker could do).
  3. Draft recommended issues and PR titles/bodies. Do not open them.
  4. Never push to main. Never change branch protection, required reviewers, or org policies.

4. How to validate the result

Each finding cites a setting, file, or workflow. No invented scanners. Main is untouched. Branch protection is unchanged.

5. What to return

Hygiene pack: Findings, Recommended issues, Recommended PRs, Out of scope, Action log.

6. What requires approval

Do not push, merge, publish, or change production. Do not edit branch protection or org security settings. Filing issues waits for the owner.

Type / in the composer to reference a saved skill. If it does not appear, open Settings → Plugins → Yours and enable it for this Bot.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.