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/dryvist/claude-code-plugins/git-workflow-standardsnpx skills add dryvist/claude-code-plugins --skill git-workflow-standardsgit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWhat 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 | $0.00059 | $0.01121 |
| Opus 5 | $0.00030 | $0.00561 |
| Sonnet 5 | $0.00012 | $0.00224 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
git-workflow-standards 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 2d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Workflow Standards
Worktree Structure
All development uses dedicated worktrees. Never work directly on the default
branch — main on a trunk repo, develop on a git-flow repo.
Create a worktree for the change; remove it when the work is done.
Every branch with commits MUST have an associated PR. Orphaned branches must get a PR or be deleted.
Stale branch (worktree-paired, bare local, or remote-only — see
prune-branches, github-workflows, for the full procedure): a non-default
branch, checked out nowhere, unreferenced by any open PR (--head or
--base), with no uncommitted changes (when a worktree exists), and either
a merged PR whose headRefOid matches the branch tip, or zero commits ahead
of the default branch. Use git worktree remove (never --force) for
worktree-paired branches — Git blocks removal of dirty worktrees — and
git push origin --delete for a live remote ref, only after
prune-branches's pre-push ancestry re-check.
Branch Hygiene
- Sync the default branch daily:
git pull - Long-running branches: rebase from the default branch weekly
- Before PRs: ensure branch is on the latest default branch
- Never branch from feature branches — always from the default branch fresh
(git-flow repos:
git flow feature startbranches fromdevelop) - Commit messages: conventional-commit prefixes only, no emoji (see
pr-standards)
Git Flow Repositories
For repositories using the Git Flow model (where the default branch is develop):
- Target Branch: All feature and bugfix branches must target and merge into
develop. - Validation: Once changes are merged into
develop, they must be thoroughly validated against production/tested ondevelop. - End-of-Session Promotion: At the end of every session, all changes on
developMUST be merged intomainvia/promote-release. This promotion is a mandatory, non-optional step. - Planning Checklist: You must explicitly add "Merge develop into main (promote release)" to your session to-do / plan checklist at the start of work.
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.
- 2d ago First seen · 100 lines · 59 tokens per session scan A f767dc962fb5
git-workflow-standards is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,121 once invoked, about $0.0003 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
draper-decorators
This skill should be used when the user asks to "create a decorator", "write a decorator", "move logic into decorator", "clean logic out of the view", "isn't it decorator logic", "test a decorator", or mentions Draper, keeping views clean, or representation logic in decorators. Should also be used when editing…
rspec
This skill should be used when the user asks to "write specs", "create spec", "add RSpec tests", "fix failing spec", or mentions RSpec, describe blocks, it blocks, expect syntax, test doubles, or matchers. Should also be used when editing spec.rb files, working in spec/ directory, planning implementation phases that…
activerecord
This skill should be used when the user asks to "write a migration", "add a column", "add column to table", "create an index", "add a foreign key", "set up associations", "fix N+1 queries", "optimize queries", "add validations", "create callbacks", "use eager loading", or mentions ActiveRecord, belongsto, hasmany…
dragonruby
This skill should be used when the user asks to "create a game", "make a game", "game development", "dragonruby", "drgtk", "game loop", "tick method", "sprite rendering", "game state", or mentions args.outputs, args.state, args.inputs, coordinate system, collision detection, animation frames, or scene management.…
mcp-server
This skill should be used when the user asks to "create an MCP server", "build MCP tools", "define MCP prompts", "register MCP resources", "implement Model Context Protocol", or mentions the mcp gem, MCP::Server, MCP::Tool, JSON-RPC transport, stdio transport, or streamable HTTP transport. Should also be used when…
ratatui-ruby
This skill should be used when the user asks to "create a TUI", "terminal interface", "terminal UI", "ratatui", "ratatui-ruby", "inline viewport", "full-screen terminal app", "terminal widgets", "tui.draw", "tui.pollevent", or mentions RatatuiRuby.run, managed loop, terminal rendering, Tea MVU, or building CLI…