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/ibrain-bvba/gutt-claude-code-plugin/github-workflownpx skills add iBrain-BVBA/gutt-claude-code-plugin --skill github-workflowgit clone --depth 1 https://github.com/iBrain-BVBA/gutt-claude-code-pluginWhat 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 | $0.00116 | $0.01655 |
| Opus 5 | $0.00058 | $0.00827 |
| Sonnet 5 | $0.00023 | $0.00331 |
| Haiku 4.5 | $0.00012 | $0.00166 |
Grade A, and why
github-workflow 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.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Workflow
Announce: "Following gutt GitHub workflow..."
The Rule
All code changes go through PRs with Copilot review. This is the quality gate — Copilot reviews every PR and does one last iteration before the code lands.
Committing to feature branches is fine and expected. What's not allowed is pushing directly to the default branch or merging without Copilot review.
Which toolchain — check, don't assume
Two paths exist and most sessions have only one of them. Establish which before you plan the delivery, not after you've announced a sequence you can't run:
- GitHub MCP (
mcp__github__*) — present in Cowork and in sessions with the GitHub MCP server connected. Probe with ToolSearch; do not assume it from the fact that this skill names those tools. ghCLI + localgit— the path in a normal Claude Code terminal session, wheremcp__github__*tools are typically absent. Verify once withgh auth status.
The rules below are toolchain-independent. Tool names are given for both.
What You Can and Can't Do
Go ahead:
- Create branches (
mcp__github__create_branch/git checkout -b) - Commit to feature branches (
mcp__github__push_files,mcp__github__create_or_update_file/git commit+git push -u origin <branch>) - Create PRs (
mcp__github__create_pull_request/gh pr create --base <base> --head <branch>) - Request Copilot review (
mcp__github__request_copilot_review/ see theghrecipe below) - Read anything — files, commits, diffs, PRs, issues
- Search code, issues, PRs
- Create/update issues
- Update PR metadata
Always ask the user first:
- Merging PRs (
mcp__github__merge_pull_request) — the user or Copilot workflow handles this
Never do:
- Push directly to
main - Merge without Copilot having reviewed
Standard Workflow
When delivering code to GitHub, follow this sequence:
- Pick the base branch deliberately — see below. It is not automatically the default branch.
- Create a feature branch from that base
- Push your code to the feature branch
- Create a PR against the same base, with a clear title referencing any Jira ticket, and a body describing what changed and why
- Request Copilot review immediately after PR creation
- Stop — let Copilot review and the user decide when to merge
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 · 120 lines · 116 tokens per session scan A afd91e97950b
github-workflow is a skill published in the GitHub repository iBrain-BVBA/gutt-claude-code-plugin (4 stars, last pushed 11d ago), licensed MIT. It adds 116 tokens to every session and 1,655 once invoked, about $0.0006 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
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
compiler-commit
Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits with the [compiler] or [rust-compiler] prefix.
commit
Commit message formatting and guidelines.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
apm-issue-autopilot
Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY…
keploy-pr-workflow
Guide for creating PRs and issues on keploy repositories — PR format, customer-data hygiene, commit conventions, sign-off. Invoke when the user asks to open, update, or review a pull request or issue, when preparing a commit that will land in main, or whenever a change is about to leave the local machine.