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/prune-branchesnpx skills add dryvist/claude-code-plugins --skill prune-branchesgit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWrote 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/dryvist/claude-code-plugins/prune-branches)<a href="https://agentmods.dev/skills/dryvist/claude-code-plugins/prune-branches"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/prune-branches.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 | $0.00048 | $0.01479 |
| Opus 5 | $0.00024 | $0.00740 |
| Sonnet 5 | $0.00010 | $0.00296 |
| Haiku 4.5 | $0.00005 | $0.00148 |
Grade A, and why
prune-branches 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 4d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prune Branches
Delete branches and worktrees carrying no unique, unmerged work: local, remote, or both.
State warning: Branch state, remote tracking, and PR status change between invocations. Re-run every git/gh command from the top on each run.
Protected
Skip these before computing staleness, on every pass below — each pass re-checks independently:
- The default branch (
main/master/develop) and any branch checked out in a worktree. Git enforces this for passes 1–2 viabranch -d/-D; pass 3 deletes a different ref, so check explicitly there too. - Any branch an open PR references as
--heador--base—--basecatches a stacked PR's target.
Build the open-PR reference set once, at the top of the run, not per branch:
gh pr list --state open --json number,headRefName,baseRefName --limit 200
Union headRefName and baseRefName into one set; test membership against
it in every pass below instead of a per-branch gh pr list call.
Stale
A branch clears Protected and meets either:
- Zero commits ahead of the default branch —
git merge-base --is-ancestor <ref> origin/<default>(equivalent togit log origin/<default>..<ref> --onelinereturning nothing). Ignores[gone]status — the ancestor check, not[gone], is the real "merged" signal. Run the default-branch guard first:origin/mainis routinely an ancestor oforigin/developon a git-flow repo. - A merged PR (most recent by
mergedAt) whoseheadRefOidmatches the branch tip —gh pr list --state merged --head <branch> --json number,headRefOid,mergedAt. Needed for squash-merges, where the branch's own commits are never literal ancestors of the default branch.
Passes
Three passes, one per ref shape:
- Worktree-paired branches —
git worktree list(skip bare repo entries). If Stale:git worktree remove <path>— never--force; a dirty worktree blocks removal, report and skip. Thengit branch -d <branch>(fall back to-Donly when the merged-PRheadRefOidmatched the branch tip before removal — a squash-merged branch unreachable from local default). - Bare local branches — local branches with no worktree
(
git for-each-ref refs/heads, excluding pass-1 branches). If Stale:git branch -d <branch>(same-Dfallback as pass 1). - Remote-only branches — remote branches with no local ref
(
git branch -r, excludingorigin/HEADand anything with a local counterpart). Check Stale againstorigin/<branch>directly; its only action is the remote delete below.
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.
- 4d ago First seen · 133 lines · 48 tokens per session scan A 458fee0b811d
prune-branches is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 1,479 once invoked, about $0.0002 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
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.…
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…
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…