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/refresh-reponpx skills add dryvist/claude-code-plugins --skill refresh-repogit 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/refresh-repo)<a href="https://agentmods.dev/skills/dryvist/claude-code-plugins/refresh-repo"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/refresh-repo.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 | $0.00035 | $0.01491 |
| Opus 5 | $0.00017 | $0.00745 |
| Sonnet 5 | $0.00007 | $0.00298 |
| Haiku 4.5 | $0.00003 | $0.00149 |
Grade A, and why
refresh-repo 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Refresh
Check open PR merge-readiness status and sync the local repository with its default branch.
State warning: Branch state, remote tracking, and PR status change between invocations. Re-run all git/gh commands from Step 1.
Steps
1. Identify Open PRs
CRITICAL: Always check for open PRs, regardless of current branch.
# Check for PR from current branch
gh pr view --json state,number,title 2>/dev/null
# ALWAYS also check for any open PRs by the user
gh pr list --author @me --state open --json number,title,headRefName
2. Report Merge-Readiness Status
For each open PR, check and report.
Run the canonical PR-readiness gate from /gh-cli-patterns.
Replace <OWNER>, <REPO>, <PR_NUMBER> per the placeholder legend in that skill.
Merge-ready criteria — all of the following must hold:
| Field | Required | Status |
|---|---|---|
state |
OPEN |
Not ready |
mergeable |
MERGEABLE |
Not ready |
mergeStateStatus |
CLEAN or HAS_HOOKS |
Not ready (BEHIND, BLOCKED, DIRTY, UNSTABLE, UNKNOWN, DRAFT) |
isDraft |
false |
Not ready |
reviewDecision |
APPROVED or null |
Not ready |
statusCheckRollup.state |
SUCCESS |
Not ready |
All reviewThreads.isResolved |
true |
Not ready — unresolved threads |
reviewThreads.pageInfo.hasNextPage |
false |
Not ready — >100 threads, paginate |
3. Sync Workflow
- Record the current branch and worktree path.
- Fetch origin with stale remote branch pruning, but without tag updates:
git fetch origin --no-tags --prune --force - Determine the default branch from
origin/HEAD, falling back tomainormaster. - Restore the default-branch worktree to the default branch. If a
worktree is checked out to the default branch, keep it on the default
branch. After a feature PR merges, that worktree is sometimes left on the
now-
[gone]feature branch. Detect and fix:- Resolve the default worktree path from
git worktree list --porcelain, matching on thebranch refs/heads/<default>entry — do not rely on basename matching of paths, since a feature branch namedfeature/<default>would also produce a path basename of<default>. - If that path exists and
git -C <path> rev-parse --abbrev-ref HEADdoes not equal<default>(this is safer thansymbolic-ref --short HEAD, which errors on detached HEAD during a rebase or commit-checkout):- If the worktree has uncommitted changes
(
git -C <path> status --porcelainis non-empty), stash them first withgit -C <path> stash push -u -m "refresh-repo: auto-stash before <default> restore"and surface the stash reference in the summary so the user can recover. git -C <path> checkout <default>.
- If the worktree has uncommitted changes
(
- Never use
--force, never discard uncommitted work, never reset.
- Resolve the default worktree path from
- Sync the default branch from its dedicated worktree with a fast-forward only merge,
using
git -C <path>so the merge always targets the default worktree regardless of the current shell directory:git -C <path> merge --ff-only origin/<default>. If the default worktree is dirty or divergent, report it and skip instead of resetting. - Conclude the operation without switching branches. Because Steps 4 and 5 used
git -C <path>to operate on the default worktree directly, the current shell's working directory and branch were never changed — each worktree owns its checkout.
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 · 132 lines · 35 tokens per session scan A f6cf14cd543e
refresh-repo is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 1,491 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…