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 agentmods add skills/rundesk-ai/rundesk-cli/managing-githubnpx skills add rundesk-ai/rundesk-cli --skill managing-githubgit clone --depth 1 https://github.com/rundesk-ai/rundesk-cliWrote 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/rundesk-ai/rundesk-cli/managing-github)<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>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 | $0.00134 | $0.01191 |
| Opus 5 | $0.00067 | $0.00596 |
| Sonnet 5 | $0.00027 | $0.00238 |
| Haiku 4.5 | $0.00013 | $0.00119 |
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.
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.
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.
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.
- 3d ago First seen · 95 lines · 134 tokens per session scan A 45af219e795d
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.
Other skills, from other repositories
release
Release a new version of Keen Agent.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
tutti-app-release
Set up, review, run, or debug external repositories that publish a Tutti workspace app through the reusable Tutti App Release GitHub Actions workflow. Use for caller workflows, tutti.app.json manifests, @tutti-os/app-release-tools, S3/CloudFront release hosting, latest.json, versions.json, catalog.json, catalog-only…
pinned-release-checklist
Minimal guidance-only Skill used by release-pinned compatibility examples.
Release Checklist
Check release readiness and record a release note. Use for release and rollback requests.
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.