gh-attach: Skill for Claude Code

.agents/skills/probot-settings/SKILL.md

probot-settings is a skill for Claude Code, Codex from Addono/gh-attach. It costs 66 tokens per session (806 once invoked), scanned A, original, MIT.

A skill for creating or updating `.github/settings.yml`, a configuration file used by the Repository Settings GitHub App to manage repository options. It checks the repository and existing labels before making targeted changes.

In plain words
What is it for?
Use it to configure GitHub repository settings, labels, merge behavior, issues, wikis, topics, environments, or branch protection through the settings file.
Why use it?
It helps keep repository settings aligned with the current project and preserves existing configuration intent. It also provides commands for checking options such as merge methods, labels, and branch protection when needed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Addono/gh-attach's own configuration. It tells Claude Code and Codex how to work on gh-attach 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 gh-attach configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Addono/gh-attach. 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/Addono/gh-attach/main/.agents/skills/probot-settings/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Addono/gh-attach

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 probot-settings

README.md
[![agentmods](https://agentmods.dev/badge/skills/addono/gh-attach/probot-settings/github.svg)](https://agentmods.dev/skills/addono/gh-attach/probot-settings)
Your own site
<a href="https://agentmods.dev/skills/addono/gh-attach/probot-settings"><img src="https://agentmods.dev/badge/skills/addono/gh-attach/probot-settings/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 probot-settings

Your own site · 80×15
<a href="https://agentmods.dev/skills/addono/gh-attach/probot-settings"><img src="https://agentmods.dev/badge/skills/addono/gh-attach/probot-settings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 806 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 $0.00066 $0.00806
Opus 5.5 $0.00026 $0.00322
Sonnet 5.5 $0.00013 $0.00161
Haiku 4.5 $0.00007 $0.00081

Measured 2mo ago against content hash 685ed618e900, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

probot-settings 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 2mo 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.

.agents/skills/probot-settings/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Probot Settings

Use this skill when a repository needs a new or updated .github/settings.yml managed by the Repository Settings GitHub App (repository-settings/app) or the older Probot Settings docs.

Step 0 — Determine Scope

Default to the current repository unless the user explicitly names another one.

gh repo view --json nameWithOwner -q .nameWithOwner
# Fallback:
git remote get-url origin

Step 1 — Gather the Current State

If .github/settings.yml already exists, read it first and update it surgically.

If the file does not exist yet, inspect the live repository and current labels:

REPO=<owner/repo>

gh repo view "$REPO" --json \
  name,nameWithOwner,description,homepageUrl,isPrivate,hasIssuesEnabled,hasWikiEnabled,defaultBranchRef,mergeCommitAllowed,rebaseMergeAllowed,squashMergeAllowed,deleteBranchOnMerge,repositoryTopics

gh label list --repo "$REPO" --json name,color,description --limit 200

Only inspect advanced sections when you actually plan to manage them:

  • Branch protection: gh api repos/$REPO/branches/<branch>/protection
  • Environments: gh api repos/$REPO/environments
  • Teams / collaborators: inspect only for organisation-owned repositories

See references/sections-and-gotchas.md for section-level guidance.

Step 2 — Build the File from Minimal to Specific

Prefer a small, accurate file over a giant aspirational one.

  1. Start with repository: and preserve the real repo name, description, homepage, visibility, default branch, and merge strategy.
  2. Add labels: next; preserve existing labels unless the user wants a deliberate cleanup.
  3. Add teams, collaborators, branches, environments, or milestones only when the repo already uses them or the user explicitly asks for them.
  4. Keep comments short and useful; follow the existing file style if one already exists.

Use references/addono-examples.md for Addono-flavoured patterns and example repos.

Step 3 — Encode Important Upstream Rules

Read the full file on GitHub · 93 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 93 lines · 66 tokens per session scan A 685ed618e900

Subscribe to this mod's changes

probot-settings is a skill published in the GitHub repository Addono/gh-attach (5 stars, last pushed 3d ago), licensed MIT. It adds 66 tokens to every session and 806 once invoked, about $0.0003 per session on Opus 5.5. 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

probot-settings compared with skills from other repositories

probot-settings next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
probot-settingsAddono/gh-attachSkill53d agoMITA66Claude Code, Codex
merge-batchdiegosouzapw/OmniRouteSkill83k6d agoMITA46Claude Code
prowler-commitprowler-cloud/prowlerSkill15kyesterdayApache-2.0A44Claude Code, Codex
gh-auth-isolationgithub/gh-awSkill5.6kyesterdayMITA20Claude Code, Codex
github-skillzeenie-ai/OpenCompanySkill1.1kyesterdayMITA51Claude Code
comet-githubrpamis/cometSkill3.3kyesterdayMITA72Claude Code, Codex
release-helperSahir619/fable-methodSkill2.3k1mo agoMITA43Claude Code