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 cosmicstack-labs/mercury-agent-skills --skill git-workflowgit clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skillsWrote 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/cosmicstack-labs/mercury-agent-skills/git-workflow)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/git-workflow"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/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/cosmicstack-labs/mercury-agent-skills/git-workflow"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/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 Tool Misuse · line 190 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 39 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00018 | $0.01598 |
| Opus 5.5 | $0.00007 | $0.00639 |
| Sonnet 5.5 | $0.00004 | $0.00320 |
| Haiku 4.5 | $0.00002 | $0.00160 |
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 1mo 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Workflow
Master the fundamentals of version control collaboration — from branching strategy to commit hygiene to review culture.
Core Principles
1. Commits Are Communication
Every commit message is a message to your future self and your teammates. Write for the reader who needs to understand why a change was made, not just what changed.
2. Branch Intentionally
Your branching strategy should match your team size, release cadence, and deployment model. The best strategy is the one your team actually follows consistently.
3. Review With Empathy
Code review is a conversation, not an inspection. The goal is shared understanding and improved quality, not catching mistakes.
4. Rebase Thoughtfully
History matters. Clean history helps debugging and release management. But never rebase shared branches without team coordination.
Git Workflow Maturity Model
| Level | Branching | Commits | Reviews | CI |
|---|---|---|---|---|
| 1: Ad-hoc | All on main | "Update" messages | None | None |
| 2: Basic | Feature branches | Some context in messages | Occasional | Lint checks |
| 3: Standard | Trunk-based or GitFlow | Conventional commits | Required PRs | Full test suite |
| 4: Advanced | Short-lived branches | Atomic, rebased commits | Automated + manual | Deploy previews |
| 5: Elite | Feature flags on trunk | Semantic versioning from commits | Async + sync pairing | Auto-deploy to prod |
Target: Level 3+ for team projects. Level 4+ for high-velocity teams.
Actionable Guidance
Branching Strategies
Trunk-Based Development (Recommended for most teams)
- Main branch: Always deployable. Protected — no direct pushes.
- Feature branches: Short-lived (1-2 days max). Branch from main, merge back to main.
- Release branches: Cut from main at release time. Bug fixes cherry-picked.
main: o---o---o---o---o---o---o
\ /
feature-A: o---o---o
\
feature-B: o---o
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.
- 1mo ago First seen · 194 lines · 18 tokens per session scan A bed2d4924ed0
git-workflow is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (485 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,598 once invoked, about $0.0001 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
antfu-create-pr
Create a reviewable GitHub pull request from the current branch with a Conventional Commits title, a concise evidence-based body, and before/after screenshots for UI changes. Use when asked to open, create, publish, or prepare a PR.
create-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
codex-review
Professional code review with auto CHANGELOG generation, integrated with Codex AI.
implement-suggestion
Implements review-comment suggestions across one or more PRs. Multi-PR mode (default when $ARGUMENTS holds PR URLs; empty $ARGUMENTS auto-detects the active PR) resolves a worktree per PR, fetches every actionable comment from human teammates AND AI review bots (claude[bot], coderabbitai[bot], …), validates each…
pr-review
One-shot read-only review of a GitHub PR — dispatches the pr-reviewer agent and reports its verdict and findings without touching your code. The short entry point for "review this PR" when you do not want an apply-and-converge loop. Also writes maintainer relevance rules via /pr-review remember . Invoke with…
azure-repos
Expert knowledge for Azure Repos development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when managing Git/TFVC repos, branch policies/PR checks, TFVC→Git migrations, large files, or…