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/d-o-hub/github-template-ai-agents/git-github-workflownpx skills add d-o-hub/github-template-ai-agents --skill git-github-workflowgit clone --depth 1 https://github.com/d-o-hub/github-template-ai-agentsWhat 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 | $0.00129 | $0.02253 |
| Opus 5 | $0.00064 | $0.01126 |
| Sonnet 5 | $0.00026 | $0.00451 |
| Haiku 4.5 | $0.00013 | $0.00225 |
Grade A, and why
git-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 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.
How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git-GitHub Workflow Skill
Unified atomic state-machine workflow: validate → commit → check issues → create PR → monitor ALL Actions → fix (swarm/web research) → merge (strategy selection) → post-merge validate
When to Use
- User asks to commit code, create a PR, push changes, or merge
- Need to manage the full git lifecycle from commit to merge
- Even if they just say "push it" or "ship it"
Overview
Orchestrates complete code submission as a state machine with swarm agent coordination and 8 phases. See references/SWARM.md for agents and references/HANDOFF.md for coordination.
Workflow Phases
Phase 0: PRE_COMMIT (Validation)
- Run quality gate with zero warnings policy
- Scan for secrets in staged changes
- Verify not on protected branch (main/master)
- Check gh CLI authentication
- Failure: Abort immediately, no changes made
Phase 1: ATOMIC COMMIT (Agent: commit-agent)
- Stage ALL changes (
git add -A) - Create atomic commit with conventional format
- Auto-detect commit type from changed files
- Generate meaningful commit message
Phase 2: CHECK GITHUB ISSUES (Agent: issue-agent)
- List open issues in repository
- Check issue relevance to current changes
- Identify blocking issues (labeled "blocking"/"critical")
- Determine if issues need fixing before merge
Phase 3: CREATE PR (Agent: pr-agent)
- Push to new feature branch (auto-generated or custom name)
- Create comprehensive PR with commit summary and context
- Link related issues in PR body
- Auto-detect existing PR for the branch
Phase 4: MONITOR ALL ACTIONS (Agent: monitor-agent)
CRITICAL: ALL GitHub Actions must pass, including pre-existing
- Monitor PR checks continuously (
gh pr checks) - Check ALL repository workflows (
gh run list) - Distinguish pre-existing vs new issues
- Detect warnings (configurable fail-on-warning)
- Wait for ALL checks green or timeout
- Branch protection awareness
Phase 5: ISSUE RESOLUTION (Agent: fix-agent) [Conditional]
What ships with it
9 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.
- evals/evals.json 3.0 KB
- evals/README_ATOMIC_COMMIT.md 4.6 KB
- evals/README_GITHUB_WORKFLOW.md 8.5 KB
- evals/README.md 1.2 KB
- references/HANDOFF.md 2.5 KB
- references/IMPLEMENTATION_ATOMIC_COMMIT.md 6.8 KB
- references/IMPLEMENTATION_GITHUB_WORKFLOW.md 9.6 KB
- references/SWARM.md 3.6 KB
- run.sh 25 KB runs code
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.
- yesterday First seen · 241 lines · 0 tokens per session scan A da215ed7ad72
git-github-workflow is a skill published in the GitHub repository d-o-hub/github-template-ai-agents (2 stars, last pushed yesterday), licensed MIT. It adds 129 tokens to every session and 2,253 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-flow-pr
Executes the full PR-driven development workflow: create an isolated feature branch from the current work, commit all staged changes, rebase cleanly onto the selected base branch (skipping any ancestor commits already merged), push the branch, and open a GitHub pull request linked to a related issue. Includes guidance…
memory-continuity
Preserves cross-session continuity with deterministic MEMORY.md, index.md, and snapshot handoffs under .agentic/memories/.
new-gh-issue-orchestration
Orchestrates a GitHub-issue-driven delivery workflow from issue intake to PR creation using reviewer-first then worker execution. Invoked when the user provides a GitHub issue link/number and asks to start end-to-end delivery.
git-worktree-workspaces
Sets up and uses Git worktrees for parallel task workspaces in the same repository clone, including safe cleanup of local worktrees. Invoked when the user asks to work on multiple branches at once, isolate tasks without extra clones, or create/remove worktrees.
client-approval
Draft a clean client approval request, set a 48h SLA with a 72h escalation, and track revision rounds so the third billable revision never slips through unbilled.
shooting-day
Plan a production day end to end — order of day, categorised shot list, equipment checklist and a WhatsApp-ready crew briefing so nobody shows up asking where the call sheet is.