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/lanegrid/agtrace/git-workflownpx skills add lanegrid/agtrace --skill git-workflowgit clone --depth 1 https://github.com/lanegrid/agtraceWhat 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 | $0.00031 | $0.02001 |
| Opus 5 | $0.00015 | $0.01001 |
| Sonnet 5 | $0.00006 | $0.00400 |
| Haiku 4.5 | $0.00003 | $0.00200 |
Grade A, and why
git-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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Workflow and Conventions
Worktree-aware Git workflow using mise run git:* tasks.
Quick Reference
# Basic operations
mise run git:status # Show current state + next action
mise run git:home # Switch to home branch + sync with origin/main
mise run git:new <branch> # Create new branch from origin/main
mise run git:cleanup [branch] # Delete merged branch + return to home
# PR lifecycle (CI wait -> browser open -> merge watch -> cleanup)
mise run git:open-pr <pr#> # All-in-one: CI -> open -> watch -> cleanup
# Pause / discard / undo
mise run git:pause [message] # WIP commit + return to home (for switching tasks)
mise run git:abandon # Discard all changes + return to home
mise run git:undo # Soft reset HEAD~1 (undo last commit)
# Stacked PRs
mise run git:sync # Sync current branch after base PR merge
Note: These tasks use the
gwRust CLI (crates.io). Install withcargo install git-workflow.
Pitfalls
- Do not run
git checkout main— usemise run git:homeinstead (worktree conflict)- Do not use
git stash— usemise run git:pauseinstead (creates WIP commit for safer worktree switching)- Do not manually rebase stacked PRs — use
mise run git:syncinstead (updates GitHub PR base + rebases)
Standard Workflow: Code -> PR
Every code change should become a PR. Follow this flow:
1. Branch -> mise run git:new -- feature/your-feature
2. Code -> make changes
3. Commit -> git add -A && git commit -m "feat: ..."
4. Push -> git push -u origin feature/your-feature
5. PR -> gh pr create -a "@me" -t "feat: ..."
6. Open -> mise run git:open-pr <pr#> (CI wait -> browser -> merge watch -> cleanup)
⚠ Run ONCE after final push. If CI fails, stop watcher -> fix -> push -> relaunch.
7. Cleanup -> (auto: merge detected -> git:cleanup runs)
git:open-pr — PR Lifecycle Management (Claude Code Background Task)
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 · 230 lines · 31 tokens per session scan A baa766c74840
git-workflow is a skill published in the GitHub repository lanegrid/agtrace (59 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 2,001 once invoked, about $0.0002 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
ship
Fully automated ship workflow. Merges the base branch, runs tests, audits coverage, reviews the diff, generates a CHANGELOG entry, bumps the version, commits, pushes, and creates the PR. Use when asked to "ship", "create a PR", or "open a pull request".
plan-ceo-review
Mega plan review from a product/CEO perspective. Challenges premise, challenges scope, maps alternatives, reviews architecture through 11 sections, and offers an outside voice. Use when asked to "CEO review", "mega plan review", "product review this plan", or when shipping a significant new product feature.
plan-eng-review
Engineering plan review. Reviews a plan document for architecture, code quality, test coverage, and performance before implementation begins. Produces a coverage diagram, failure modes map, and parallelization strategy. Use when asked to "review this plan", "eng review", or "architecture review".
retro
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics for the time window. Team-aware: identifies the user, then analyzes every contributor with per-person praise and growth opportunities. Use when asked for a "retro", "engineering retrospective", or "weekly summary".
review
Pre-merge code review — the single canonical review of a change before it lands. Covers BOTH diff safety/structure (SQL safety, LLM trust-boundary violations, conditional side effects) AND engineering quality (architecture fit, edge cases, test coverage, performance). Use when asked to "review this PR", "code review"…
health
Code Quality Dashboard. Runs the project's type-checker, linter, test runner, and dead-code detector, scores each category 0-10, and presents a dashboard with trends. Use when asked for a "health check", "code quality report", or "quality dashboard".