github

A set of GitHub working rules for commits, branches, issues, and pull requests. It explains when to work directly on the main branch and when to create a short-lived branch.

In plain words
What is it for?
Use it when committing code, creating branches, opening issues or pull requests, or deciding how to structure a change.
Why use it?
It helps keep project history and code reviews understandable, while reducing unnecessary branching and vague change descriptions.

Skill for Claude CodeCodex

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/robconery/cassini-workshop/github
Any agent
npx skills add robconery/cassini-workshop --skill github
Clone the repo
git clone --depth 1 https://github.com/robconery/cassini-workshop

Made for: Claude Code, Codex.

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,511 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 $0.00083 $0.01511
Opus 5 $0.00042 $0.00756
Sonnet 5 $0.00017 $0.00302
Haiku 4.5 $0.00008 $0.00151

Measured yesterday against content hash 6106a7e4b318, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github 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 yesterday.

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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

  • github — 100% identical, 0 lines differ
  • github — 100% identical, 0 lines differ
.claude/skills/github/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub workflow

The point: write commits, issues, and PRs that read clearly weeks later. Be direct, be specific, skip the filler.

Branching — when to branch, when not

Trunk-based (commit straight to main) when:

  • Single-file or single-concept fix.
  • Typo, doc tweak, version bump, comment, lint fix.
  • Test-only addition that doesn't change behavior.
  • Anything that takes one commit and reviews itself in 30 seconds.

Short-lived branch when:

  • More than ~2 commits expected.
  • New feature or capability, even a small one.
  • Schema/migration change.
  • Anything that could break main for someone else.
  • A spec / plan task that has its own id (e.g. T052 from docs/PLAN.md).

Branch naming: <type>/<short-slug> — type is one of feat, fix, chore, docs, refactor, test. Examples:

feat/order-fulfillment-tx
fix/signature-verify-header-case
chore/bump-drizzle

Keep branches short-lived. Open the PR early, even as draft.

Commits — Conventional Commits, kept honest

Format:

<type>(<optional scope>): <imperative summary, lower-case, no period>

<body — what changed and why, wrapped at ~72 cols>

<footer — refs, breaking changes>

Types: feat, fix, chore, docs, refactor, test, perf, build, ci, revert.

Summary line rules:

  • 50 chars or fewer when possible, hard cap 72.
  • Imperative mood (add, not added/adds).
  • No trailing period.
  • Scope is optional; use it when there's an obvious area (feat(webhook): …, fix(db): …).

Body rules:

  • Always include one if the change isn't self-evident from the diff.
  • Explain what changed and why — never restate the diff line by line. Mention trade-offs or alternatives rejected if relevant.
  • One blank line between summary and body.
  • Reference issues with Refs #123 or Closes #123.

Footers:

  • Closes #N to auto-close an issue on merge.
  • BREAKING CHANGE: <what breaks, how to migrate> for breakages.
  • Co-Authored-By: lines when pairing.

Read the full file on GitHub · 212 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. yesterday First seen · 212 lines · 83 tokens per session scan A 6106a7e4b318

Subscribe to this mod's changes

github is a skill published in the GitHub repository robconery/cassini-workshop (1 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 1,511 once invoked, about $0.0004 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

supermemory

Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long-term context retention, or semantic search across knowledge bases. It provides Memory API for learned user context, User Profiles for…

supermemoryai/supermemory · 81 tokens

frontmcp-setup

Use when starting, scaffolding, or organizing a FrontMCP project. Covers creating a new project (CLI scaffold or manual) for Node, Vercel, and other targets; standalone versus Nx-monorepo layout, naming conventions, generators, and dependency rules; composing multiple @App classes, ESM packages, and remote MCP servers…

agentfront/frontmcp · 176 tokens

hono-core

Hono ultrafast web framework fundamentals - routing, context, handlers, and response patterns for multi-runtime deployment.

bobmatnyc/claude-mpm-skills · 26 tokens

mooncite

Use when an agent needs past Pi, OMP, Claude Code, Codex, or ChatGPT context.

WhenMoon-afk/claude-memory-mcp · 26 tokens

release

Drive the AR.IO Node release process end-to-end — preflight checks, prepare commit, finalize with image SHAs, test docker compose profiles, tag & publish, and post-release cleanup. Use when the user says "cut a release", "prepare release N", "finalize the release", or similar.

ar-io/ar-io-node · 64 tokens

testing

Decision guide for testing in the ar-io-node repo — which test layer to use, how to run it, and which helpers to reach for. Use when writing a new test, picking a layer (unit / property / e2e / auto-verify / parquet integration / load test), running the suite or a single file, debugging a test failure, or when a…

ar-io/ar-io-node · 0 tokens