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 rjmurillo/ai-agents --skill git-advanced-workflowsgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/git-advanced-workflows)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/git-advanced-workflows"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/git-advanced-workflows/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/rjmurillo/ai-agents/git-advanced-workflows"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/git-advanced-workflows.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 40 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.
- high Tool Misuse · line 127 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.
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 | $0.00082 | $0.02677 |
| Opus 5.5 | $0.00033 | $0.01071 |
| Sonnet 5.5 | $0.00016 | $0.00535 |
| Haiku 4.5 | $0.00008 | $0.00268 |
Grade A, and why
git-advanced-workflows scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Advanced Workflows
Advanced Git techniques for clean history, effective collaboration, and confident recovery.
Triggers
| Trigger Phrase | Operation |
|---|---|
rebase my branch |
Interactive or standard rebase guidance |
cherry-pick a commit |
Cherry-pick with conflict resolution |
find the breaking commit |
Git bisect workflow |
recover lost commits |
Reflog exploration and recovery |
use git worktrees |
Worktree setup, management, and live-versus-abandoned triage |
Process
Phase 1: Assess the Situation
- Identify which workflow applies (rebase, cherry-pick, bisect, worktree, recovery)
- Check current branch state:
git status,git log --oneline -10 - Create a safety branch before any destructive operation:
git branch backup-<timestamp>- macOS/Linux (bash/zsh):
git branch backup-$(date +%s) - Windows PowerShell:
git branch backup-$(Get-Date -UFormat %s)
- macOS/Linux (bash/zsh):
Phase 2: Execute the Workflow
Rebase: Clean Up Feature Branch Before PR
git checkout feature/user-auth
# Record the remote tip BEFORE rewriting. A later fetch moves the tracking
# ref, so reading it at push time would let the lease overwrite new commits.
git fetch origin
EXPECTED_REMOTE_SHA=$(git rev-parse origin/feature/user-auth)
git rebase -i main
# Squash "fix typo" commits, reword messages, reorder logically
git push --force-with-lease="refs/heads/feature/user-auth:$EXPECTED_REMOTE_SHA" \
origin HEAD:refs/heads/feature/user-auth
Rebase operations: pick (keep), reword (change message), edit (amend content), squash (combine keeping message), fixup (combine discarding message), drop (remove).
Autosquash pattern:
git commit --fixup HEAD # Mark as fixup for previous commit
git rebase -i --autosquash main # Auto-marks fixup commits
Split a commit:
git rebase -i HEAD~3 # Mark commit with 'edit'
git reset HEAD^ # Reset commit, keep changes in working tree (unstaged)
git add file1.py && git commit -m "feat: add validation"
git add file2.py && git commit -m "feat: add error handling"
git rebase --continue
What ships with it
1 file 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.
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.
- 14d ago Changed · +5 lines 4dc115a325dd
- 15d ago Changed · +26 lines 243b1356020f
- 18d ago Changed · +6 lines 901bf34b053b
- 21d ago Changed · +13 lines · +7 tokens per session 6fb60b3a3159
- 1mo ago First seen · 183 lines · 75 tokens per session scan A f47de2380592
git-advanced-workflows is a skill published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 2,677 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
review-this-branch
Run the nohuman review gate (fresh-session adversarial reviewer + tamper guard) over the current branch or a GitHub pull request, with no server, no database, and no onboarding, and relay the pass/fail checklist.
respond-to-pr-comments
Respond to pull request review comments on GitHub or Azure DevOps Services. Reads review threads, validates each, proposes fixes or explanations, applies changes with user confirmation, and updates thread status via the platform's API. Use when the user wants to address PR feedback or resolve review threads.
ai-pr
The pull-request loop, opened from the local main with no worktree: cut the pull-request branch from the local main, push it, open the pull request against main with a body assembled from the merge commits the branch carries, watch CI and the review comments, fix only what is obvious in bounded iterations, then merge…
install-gemini-code-review-action
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
review-remote
Review open PR/MR and publish findings.