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/juan294/cc-rpi/git-workflownpx skills add juan294/cc-rpi --skill git-workflowgit clone --depth 1 https://github.com/juan294/cc-rpiWrote 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/juan294/cc-rpi/git-workflow)<a href="https://agentmods.dev/skills/juan294/cc-rpi/git-workflow"><img src="https://agentmods.dev/badge/skills/juan294/cc-rpi/git-workflow.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00022 | $0.00841 |
| Opus 5 | $0.00011 | $0.00420 |
| Sonnet 5 | $0.00004 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
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 3d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Workflow
Push Sequence
Wrong -- unstaged changes break the pull:
git pull --rebase && git push
Right -- commit before pulling (clean tree required):
git add <files> && git commit -m "msg" && git pull --rebase && git push
Pull before push even on a branch you just committed to -- the remote may have advanced from other sessions or parallel agents since you last fetched.
Empty Repositories
Wrong -- git log and git diff HEAD fail on a repo with no commits yet:
git log -1
git diff HEAD
Right -- check for a HEAD first:
git rev-parse HEAD 2>&1 || echo "no commits yet -- skip log/diff HEAD"
First Push / PR Creation
Wrong -- no upstream, push and gh pr create both fail:
git push && gh pr create --title "feat: thing"
Right -- set upstream on first push:
git push -u origin <branch> && gh pr create --title "feat: thing"
Push with Tag
Wrong -- pushes ALL local tags, fails if any old tag exists on remote:
git push --tags
Right -- push specific tags by name or use --follow-tags:
git push origin main && git push origin v1.0.0
Branch Verification
Wrong -- assume branch from conversation context:
git commit -m "feat: add feature"
Right -- verify branch before every commit:
git branch --show-current && git commit -m "feat: add feature"
Worktree Management
Wrong -- relative paths and lowercase -d:
cd ../worktree && pnpm test # cwd resets between calls
git worktree remove <path> && git branch -d <branch> # -d fails
Right -- absolute paths, force remove, uppercase -D:
cd /absolute/path/to/worktree && pnpm test
git worktree remove --force <path>; git branch -D <branch>
Always remove worktrees BEFORE merging PRs with --delete-branch.
Cleanup After Merge
Wrong -- assume the merge cleaned up; leave stale local branches behind (a cleanup "done" that left two local branches needing a second pass):
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.
- 3d ago First seen · 146 lines · 22 tokens per session scan A c4409cad534a
git-workflow is a skill published in the GitHub repository juan294/cc-rpi (5 stars, last pushed 14d ago), licensed MIT. It adds 22 tokens to every session and 841 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
weather-fetcher
Instructions for fetching current weather temperature data for Dubai, UAE from Open-Meteo API.
claude-md-review
Audit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files, stale facts, and bloat. Use when asked to review, audit, improve, shrink, or fix a CLAUDE.md, and when a project's results feel inconsistent or Claude keeps rediscovering the same context.
common-product-requirements
Standardize PRD discovery and drafting for product scope, user outcomes, requirement IDs, and acceptance criteria. Use when creating PRD, product requirements, feature specification, or acceptance criteria plan.
common-security-standards
Enforce universal security protocols for safe, resilient software. Use when implementing authentication, encryption, authorization, input validation, secret management, or any security-sensitive feature across any language or framework.
common-software-requirements
Standardize SRS and FRS specifications for technical behavior, interfaces, data contracts, quality constraints, and verification mapping. Use when writing SRS, functional specification, system behavior requirements, API/data contracts, or non-functional thresholds.
system-design-case-catalog
Answer classic system design problems as constraint-to-solution sketches and coach interview practice: URL shortener, rate limiter, news feed, chat, notification, autocomplete, crawler, unique id. Use for interview practice or naming the closest known shape for a new problem.