managing-github

managing-github is a skill for Claude Code, Codex from rundesk-ai/rundesk-cli. It costs 134 tokens per session (1,191 once invoked), scanned A, original, MIT.

A workflow guide for work that crosses into GitHub, a service for hosting code and coordinating development. It covers issues, pull requests, reviews, releases, tags, and live deployment branches.

In plain words
What is it for?
Use it when investigating repository problems, handling GitHub issues or pull requests, preparing releases, or reaching a deployment boundary.
Why use it?
It clarifies when GitHub work needs to happen and keeps ownership and safety boundaries explicit. It helps avoid making repository changes without the right request or evidence.

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/rundesk-ai/rundesk-cli/managing-github
Any agent
npx skills add rundesk-ai/rundesk-cli --skill managing-github
Clone the repo
git clone --depth 1 https://github.com/rundesk-ai/rundesk-cli

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 managing-github

README.md
[![agentmods](https://agentmods.dev/badge/skills/rundesk-ai/rundesk-cli/managing-github.svg)](https://agentmods.dev/skills/rundesk-ai/rundesk-cli/managing-github)
Your own site
<a href="https://agentmods.dev/skills/rundesk-ai/rundesk-cli/managing-github"><img src="https://agentmods.dev/badge/skills/rundesk-ai/rundesk-cli/managing-github.svg" alt="Measured on agentmods" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,191 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 $0.00134 $0.01191
Opus 5 $0.00067 $0.00596
Sonnet 5 $0.00027 $0.00238
Haiku 4.5 $0.00013 $0.00119

Measured 3d ago against content hash 45af219e795d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

managing-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 3d 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.

src/skills/managing-github/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Manage GitHub

Use one safety contract, then load only the operation reference required by the request.

Keep the ownership boundary explicit

This skill owns externally stored GitHub issues, pull requests, pull-request reviews, releases, and their readback. It does not own local implementation, development planning, technical code-review judgment, generic branch maintenance, GitHub Actions design, repository settings, permissions, rulesets, secrets, or organization administration.

The agent responsible for the overall outcome retains every GitHub mutation. A specialist may return a local branch, diff, commit, issue draft, pull-request draft, release recommendation, and evidence; it does not file, edit, push, tag, publish, request review, or follow up unless it is itself the responsible agent and the request authorizes that exact action.

Trigger from the workflow, not only the request wording

Load this skill when the active work reaches a GitHub-hosted boundary, including when:

  • investigation finds a repository defect that may need an issue, duplicate search, comment, or closure decision;
  • verified development work is ready for the repository's required branch push or pull-request path;
  • an existing pull request needs stored-state inspection, template or readiness review, an authorized review submission or update, or check follow-up;
  • a versioned change reaches the repository's release, tag, notes, asset, or branch-reconciliation contract; or
  • another in-scope repository workflow requires reading GitHub templates, rules, checks, or the authoritative hosted object before proceeding.

Do not load it merely because local code happens to be hosted on GitHub. Stay with the local development workflow until GitHub state, policy, or delivery affects the next decision.

Triggering this skill does not grant a mutation. If the workflow reveals a useful issue or pull request that the user did not authorize and repository policy does not require, inspect and prepare the artifact, then present the delivery decision instead of silently creating it.

Read the full file on GitHub · 95 lines

Files

What ships with it

6 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. 3d ago First seen · 95 lines · 134 tokens per session scan A 45af219e795d

Subscribe to this mod's changes

managing-github is a skill published in the GitHub repository rundesk-ai/rundesk-cli (4 stars, last pushed 7d ago), licensed MIT. It adds 134 tokens to every session and 1,191 once invoked, about $0.0007 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.