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/rojim666/sztucode/githubnpx skills add rojim666/SztuCode --skill githubgit clone --depth 1 https://github.com/rojim666/SztuCodeWhat 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 | $0.00053 | $0.00952 |
| Opus 5 | $0.00026 | $0.00476 |
| Sonnet 5 | $0.00011 | $0.00190 |
| Haiku 4.5 | $0.00005 | $0.00095 |
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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- github — 100% identical, 148 lines differ
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub
Overview
Use this skill as the umbrella entrypoint for general GitHub work in this plugin. It should decide whether the task stays in repo and PR triage or should be handed off to a more specific review, CI, or publish workflow.
This plugin is intentionally hybrid:
- Prefer the GitHub app from this plugin for repository, issue, pull request, comment, label, reaction, and PR creation workflows.
- Use local
gitandghonly when the connector does not cover the job well, especially for current-branch PR discovery, branch creation, commit and push,gh auth status, and GitHub Actions log inspection. - Keep connector state and local checkout context aligned. If the request is about the current branch, resolve the local repo and branch before acting.
Once the intent is clear, route to the specialist skill immediately and do not keep broad GitHub triage in scope longer than needed.
Connector-First Responsibilities
Handle these directly in this skill when the request does not need a narrower specialist workflow:
- repository orientation once the repo, PR, issue, or local checkout is identified
- recent PR or issue triage
- PR metadata summaries
- PR patch inspection
- PR comments, labels, and reactions
- issue lookup and summarization
- PR creation after a branch is already pushed
Prefer the GitHub app from this plugin for those flows because it provides structured PR, issue, and review-adjacent data without depending on a local checkout. If the repository is not already identifiable from the user request or local git context, ask for the repo instead of pretending there is a repo-search flow that may not exist.
Routing Rules
- Resolve the operating context first:
- If the user provides a repository, PR number, issue number, or URL, use that.
- If the request is about "this branch" or "the current PR", resolve local git context and use
ghonly as needed to discover the branch PR. - If the repository is still ambiguous after local inspection, ask for the repo identifier.
- Classify the request before taking action:
repo or PR triage: summarize PRs, issues, patches, comments, labels, reactions, or repository statereview follow-up: unresolved review threads, requested changes, or inline review feedbackCI debugging: failing checks, Actions logs, or CI root-cause analysispublish changes: create or switch branches, stage changes, commit, push, and open a draft PR
- Route to the specialist skill as soon as the category is clear:
- Review comments and requested changes:
../gh-address-comments/SKILL.md - Failing GitHub Actions checks:
../gh-fix-ci/SKILL.md - Commit, push, and open PR:
../yeet/SKILL.md
- Review comments and requested changes:
- Keep the hybrid model consistent after routing:
- connector first for PR and issue data
- local
gitandghonly for the specific gaps the connector does not cover
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.
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.
- 2d ago First seen · 75 lines · 53 tokens per session scan A 380d663305eb
github is a skill published in the GitHub repository rojim666/SztuCode (45 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 952 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
codex-delegate
Delegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Codex — phrasings like "have Codex do X", "delegate this to Codex", "run it through Codex", or "use Codex to implement/fix/refactor" …
commandcode-delegate
Delegate a coding task to the Command Code CLI (cmd) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Command Code — phrasings like "have Command Code do X", "delegate this to commandcode", "run it through cmd", or "use Command Code…
delegate-setup
Configure delegation fleet lanes: which implementer CLI handles which kind of work, with optional model and effort (or variant) dials. Discovers installed CLIs, proposes a lane map for user approval, and writes global or project config only after explicit yes. Use when the user asks to set up, configure, or…
opencode-delegate
Delegate a coding task to the OpenCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to OpenCode — phrasings like "have OpenCode do X", "delegate this to OpenCode", "run it through OpenCode", or "use OpenCode to…
warp-delegate
Delegate a coding task to the Warp Agent CLI (oz) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Warp - phrasings like "have Warp implement X", "delegate this to the Warp CLI", "run it through Warp", "use oz to…
zcode-delegate
Delegate a coding task to the Z.AI ZCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to ZCode — phrasings like "have ZCode do X", "delegate this to ZCode", "run it through ZCode", or "use ZCode to implement/fix/refactor" — or…