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 skills add vasilyu1983/AI-Agents-public --skill dev-git-workflowgit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/dev-git-workflow)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/dev-git-workflow"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/dev-git-workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/dev-git-workflow"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/dev-git-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Anti-Refusal · line 165 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
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 5.1 | $0.00043 | $0.03948 |
| Opus 5.5 | $0.00017 | $0.01579 |
| Sonnet 5.5 | $0.00009 | $0.00790 |
| Haiku 4.5 | $0.00004 | $0.00395 |
Grade A, and why
dev-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 9d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Workflow
Use this skill to choose a team Git model, set merge and review policy, and define safe defaults for human and AI-assisted collaboration. It assumes the reader knows Git commands; it carries the decisions.
Default bias: GitHub Flow or trunk-based development, one merge method per repository, a merge queue once PRs routinely go stale before landing, one worktree per agent, and release branches only when version support requires them. Hosting-platform features (stacked PRs, merge-queue options, ruleset fields) and Git itself change several times a year: before recommending a version-gated Git feature, check the release notes on git-scm.com; before recommending a platform feature, check that platform's docs for availability on the user's plan.
Quick Reference
| Need | Default | Reference |
|---|---|---|
| Pick a branching model | GitHub Flow; trunk-based plus merge queue at high merge concurrency | references/branching-strategies.md |
| Pick a merge method | squash for small-PR flows; merge commits for release branches | Merge Method, references/pr-best-practices.md |
| Keep main green under concurrency | merge queue or merge train | Merge Queue, references/automated-quality-gates.md |
| Land dependent changes fast | stacked PRs | references/stacked-diffs-guide.md |
| Run parallel agent or feature work | one worktree and branch per agent | references/ai-agent-worktrees.md |
| Release and hotfix | upstream-first fixes, tags from main | references/release-management.md |
| Commit messages and changelogs | owned by dev-git-commit-message | dev-git-commit-message, references/commit-conventions.md |
| Debug bad merges or regressions | conflict discipline, bisect | references/conflict-resolution.md, references/git-bisect-debugging.md |
What ships with it
24 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.
- agents/openai.yaml 376 B
- assets/ci-cd/github-pr-checks.yml 8.7 KB
- assets/ci-cd/gitlab-mr-checks.yml 7.6 KB
- assets/pull-requests/pr-template.md 3.0 KB
- assets/releases/release-workflow.md 3.6 KB
- assets/template-git-workflow-guide.md 3.3 KB
- data/sources.json 7.5 KB
- data/tweet-repos.json 28 KB
- learnings.consolidated.md 592 B
- learnings.md 1.0 KB
- references/ai-agent-worktrees.md 11 KB
- references/automated-quality-gates.md 6.5 KB
- references/branching-strategies.md 7.0 KB
- references/commit-conventions.md 2.5 KB
- references/common-mistakes.md 3.1 KB
- references/conflict-resolution.md 6.1 KB
- references/git-bisect-debugging.md 5.2 KB
- references/git-hooks-automation.md 6.5 KB
- references/interactive-rebase-guide.md 5.0 KB
- references/monorepo-workflows.md 6.2 KB
- references/pr-best-practices.md 6.8 KB
- references/release-management.md 7.0 KB
- references/stacked-diffs-guide.md 7.4 KB
- references/validation-checklists.md 4.1 KB
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.
- 9d ago Changed aea3604512f8
- 16d ago Changed · -214 lines 85ddaed80305
- 28d ago Changed · +3 lines d2d22b44dc10
- 1mo ago First seen · 388 lines · 43 tokens per session scan A 9b8f67b45818
dev-git-workflow is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (101 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 3,948 once invoked, about $0.0002 per session on Opus 5.5. 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
gh-monitor-pr
Start a detached GitHub pull-request monitor that wakes the exact launching Codex Desktop or CLI root through the managed Codex App Server when review, CI, conflict, merge-queue, closure, readiness, or merge events need attention. Use when the user asks Codex to watch, monitor, babysit, or wait on a PR or merge queue…
changelog
Generate or update CHANGELOG.md with an entry for the unreleased changes since the last git tag. Invoke when the user asks to cut a release, update the changelog, or summarize changes since v-something.
manifest
Full autonomous SDLC — design, plan, implement, review, and ship with 4 human approval gates.
seal
Ships a feature — simplify pass, certify, commit, PR, CI monitoring, review loop, merge. Use when a feature branch is verified and ready to ship.
doc-changelog
CHANGELOG maintenance following Keep a Changelog. Trigger when the user wants to document changes or prepare a release.
ship-task
Use to wrap up a finished task - set status to done, merge, clean up.