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/gh-cli-patternsnpx skills add dryvist/claude-code-plugins --skill gh-cli-patternsgit 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 | $0.00094 | $0.04161 |
| Opus 5 | $0.00047 | $0.02080 |
| Sonnet 5 | $0.00019 | $0.00832 |
| Haiku 4.5 | $0.00009 | $0.00416 |
Grade A, and why
gh-cli-patterns 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 yesterday.
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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gh CLI Canonical Patterns — github-workflows
Placeholder Convention
Two visually distinct notations — never mix them up:
| Notation | Meaning | Example |
|---|---|---|
$varName |
GraphQL variable name — keep as literal text in the query body | $prNumber |
<UPPER_NAME> |
Shell template — replace before running | <PR_NUMBER> |
Standard replacements:
<OWNER> → $(gh repo view --json owner --jq '.owner.login')
<REPO> → $(gh repo view --json name --jq '.name')
<PR_NUMBER> → $(gh pr view --json number --jq '.number') (integer)
<THREAD_ID> → PRRT_* node ID from the fetch-threads query (string)
<DATABASE_ID> → numeric comment ID from the fetch-threads query
<DEFAULT_BRANCH> → see Canonical Default-Branch Detection below
Canonical Default-Branch Detection
Repos in this org run one of two branch models. Detect which one before
using any literal main in a PR base, sync target, or merge command:
gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name'
# or, without gh: git remote show origin | grep 'HEAD branch'
<DEFAULT_BRANCH> |
Model | What it means for skills in this plugin |
|---|---|---|
main |
Trunk | main is both the default branch and production. /merge-pr merges into it with its normal default (merge commit) or --squash/-s. |
develop |
git-flow (see git-flow rule) | develop is the default integration branch — feature PRs target it, /merge-pr's default (merge commit) or --squash both apply. main is production only: merge commits only, no direct pushes, every merge triggers release-please. |
Never infer the model from the current local branch name — always read
defaultBranchRef (or origin/HEAD) fresh, since it can differ per repo and
per invocation.
A PR's own base branch (gh pr view --json baseRefName --jq '.baseRefName')
can still be main on a git-flow repo — that is a promotion PR (develop →
main), not a feature PR, and it is merge-commit-only regardless of what
this section's detection returns. See /promote-release.
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.
- yesterday First seen · 385 lines · 94 tokens per session scan A f3392423bc27
gh-cli-patterns is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 94 tokens to every session and 4,161 once invoked, about $0.0005 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…
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…
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.…