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 bybren-llc/safe-agentic-workflow --skill git-advancedgit clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflowWrote 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/bybren-llc/safe-agentic-workflow/git-advanced)<a href="https://agentmods.dev/skills/bybren-llc/safe-agentic-workflow/git-advanced"><img src="https://agentmods.dev/badge/skills/bybren-llc/safe-agentic-workflow/git-advanced/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/bybren-llc/safe-agentic-workflow/git-advanced"><img src="https://agentmods.dev/badge/skills/bybren-llc/safe-agentic-workflow/git-advanced.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 32 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 39 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 234 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 244 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 271 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 | $0.00062 | $0.01635 |
| Opus 5.5 | $0.00025 | $0.00654 |
| Sonnet 5.5 | $0.00012 | $0.00327 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade A, and why
git-advanced 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- git-advanced — 100% identical, 32 lines differ
How it starts
The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Advanced Skill
TEMPLATE: This skill uses
{{PLACEHOLDER}}tokens. Replace with your project values before use.
Purpose
Provide guidance for advanced git operations with safety considerations. This project uses a rebase-first workflow with linear history -- understand these patterns to avoid breaking the codebase.
When This Skill Applies
- Rebasing feature branches onto dev
- Using git bisect to find bugs
- Cherry-picking commits between branches
- Resolving complex merge conflicts
- Recovering from git mistakes
Stop-the-Line Conditions
FORBIDDEN Operations
# FORBIDDEN: Force push to protected branches
git push --force origin {{MAIN_BRANCH}} # NEVER
git push --force origin master # NEVER
# FORBIDDEN: Merge commits on dev branch
git merge feature-branch # Use rebase-and-merge PR strategy
# FORBIDDEN: Skip pre-commit hooks
git commit --no-verify # Hooks exist for a reason
# FORBIDDEN: Rewriting shared history
git rebase -i HEAD~5 && git push --force # If already pushed
SAFE Operations
# SAFE: Force-with-lease on your feature branch
git push --force-with-lease origin {{TICKET_PREFIX}}-XXX-feature
# SAFE: Interactive rebase before first push
git rebase -i origin/{{MAIN_BRANCH}}
# SAFE: Force push after conflict resolution on your own branch
git rebase origin/{{MAIN_BRANCH}} && git push --force-with-lease origin {{TICKET_PREFIX}}-XXX-feature
Rebase Workflow (Standard)
Before Creating PR
# 1. Fetch latest changes
git fetch origin {{MAIN_BRANCH}}
# 2. Rebase onto latest
git rebase origin/{{MAIN_BRANCH}}
# 3. If conflicts, resolve them
git status # See conflicted files
# ... edit files to resolve ...
git add <resolved-files>
git rebase --continue
# 4. Push with force-with-lease
git push --force-with-lease origin {{TICKET_PREFIX}}-XXX-feature
During PR Review (After Feedback)
# 1. Make requested changes
git add . && git commit -m "fix: address PR feedback [{{TICKET_PREFIX}}-XXX]"
# 2. Fetch and rebase again
git fetch origin {{MAIN_BRANCH}}
git rebase origin/{{MAIN_BRANCH}}
# 3. Push update
git push --force-with-lease origin {{TICKET_PREFIX}}-XXX-feature
What ships with it
3 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.
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 · 286 lines · 62 tokens per session scan A f4239c74268e
git-advanced is a skill published in the GitHub repository bybren-llc/safe-agentic-workflow (425 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 1,635 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
changelog
Auto-generate a changelog from git commits and sprint data. Internal and player-facing versions.
team-release
Orchestrate the release team — release-manager, qa-lead, devops-engineer, producer — to execute a release from candidate to deployment.
05-review
Reviews a change or a diff and says whether it is ready to ship, naming every problem with its fix. Use when the user wants a change checked before it ships. Not for fixing what the review finds, and not for auditing a whole codebase.
resolve-conflict
Resolves deterministic Git conflicts or approved choices. Use when the user wants to resolve a merge, rebase, or cherry-pick conflict. Not for deciding between competing implementations or committing changes.
00-repo-init
Initialize a project repository with git init, a default branch, a bootstrap commit, CONTRIBUTING.md, and optionally the remote. Use when the user wants to init or set up a new repo, or publish to a remote. Not for committing, opening a PR, or tagging.
01-commit
Create atomic conventional commits; safely retry scoped hook fixes; optionally push. Use when the user wants to commit changes, optionally pushing the branch. Not for amending, rebasing, opening a pull request, or tagging a release.