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 skills add qte77/claude-code-plugins --skill creating-ghagit clone --depth 1 https://github.com/qte77/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/qte77/claude-code-plugins/creating-gha)<a href="https://agentmods.dev/skills/qte77/claude-code-plugins/creating-gha"><img src="https://agentmods.dev/badge/skills/qte77/claude-code-plugins/creating-gha/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/qte77/claude-code-plugins/creating-gha"><img src="https://agentmods.dev/badge/skills/qte77/claude-code-plugins/creating-gha.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00035 | $0.01133 |
| Opus 5.5 | $0.00014 | $0.00453 |
| Sonnet 5.5 | $0.00007 | $0.00227 |
| Haiku 4.5 | $0.00003 | $0.00113 |
Grade A, and why
creating-gha 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 17d 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.
Creating GitHub Actions
Target: $ARGUMENTS
Creates a Marketplace-ready composite GitHub Action with TDD, signed commits, and proper release flow.
References
references/marketplace-checklist.md— action.yaml fields, signed commits, release flow, gotchasreferences/python-gha-patterns.md— full Python composite action walkthrough (uv, pyproject.toml, CI)references/companion-plugins.md— companion plugins by workflow phase (tdd-core, python-dev, security-audit, commit-helper, makefile-core; built-in/simplify)
Marketplace Requirements
See references/marketplace-checklist.md for full reference.
Required action.yaml fields:
name— unique on Marketplace (check before using)description— shown in search resultsbranding—icon(Feather icon name) +color(white/yellow/blue/green/orange/red/purple/gray-dark)
Scaffold
Pick the layout that matches the action's language:
Shell-based (composite with inline run: or scripts/*.sh):
action.yaml # composite action definition + branding
scripts/ # extracted shell logic (when inline run: grows too large)
tests/unit/ # BATS test files
.github/workflows/ # ci.yaml (bats + actionlint + shellcheck), release.yaml
README.md # usage example with @vN, inputs table, version badge
Python-based (composite calling uv run):
action.yaml # composite action definition + branding
src/ # Python source (app.py entry point)
tests/ # pytest tests
.github/workflows/ # ci.yaml (pytest + ruff), release.yaml
pyproject.toml # deps, ruff, bumpversion
uv.lock # committed, CI uses --frozen
README.md # usage example with @vN, inputs table, version badge
See references/python-gha-patterns.md for the full Python walkthrough.
TDD Workflow
RED — infra tests first:
# tests/unit/test_action.bats
@test "action.yaml exists" { [ -f action.yaml ]; }
@test "action.yaml has name field" { grep -q "^name:" action.yaml; }
@test "action.yaml has description field" { grep -q "^description:" action.yaml; }
@test "action.yaml has branding" { grep -q "^branding:" action.yaml; }
@test "action.yaml has runs.using composite" { grep -q "using: composite" action.yaml; }
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 17d ago Changed · +1 lines 5dd1502d02e7
- 21d ago Changed · +1 lines 4063096d0638
- 1mo ago First seen · 131 lines · 35 tokens per session scan A 3116f5bfc6ac
creating-gha is a skill published in the GitHub repository qte77/claude-code-plugins (3 stars, last pushed 4d ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,133 once invoked, about $0.0001 per session on Opus 5.5. 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
github-cli
This skill should be used when working with GitHub CLI (gh) for repository management, pull requests, issues, API access, GitHub Actions, or automation workflows. Provides comprehensive guidance on gh command patterns, security considerations, and best practices.
actions-reusable-workflows
Wire a repository to the bitwise-media-group/github-workflows reusable workflows — thin, SHA-pinned caller workflows for CI, security (CodeQL) scanning, release (release-please/GoReleaser/Zensical docs), the signature-preserving fast-forward /merge + merge-review-ack + merge-notice flows, and add-to-project — plus the…
actions-security
Security hardening for GitHub Actions workflows with a least-privilege posture — default-deny permissions ({} then minimal per-job scopes), SHA-pinning every third-party action, avoiding pullrequesttarget (and the safe trusted-event allowlist pattern when an elevated trigger is unavoidable), preventing…
actions-style
GitHub Actions workflow authoring conventions for readable, least-privilege workflows — .github/workflows/.yaml layout, explicit scoped triggers, boolean logic with truthy/falsey expressions (if ${{ inputs.flag }} over == 'true'), concurrency, matrix builds, job outputs, and authoring reusable (workflowcall) and…
actions-validate
Validate GitHub Actions workflow files locally with the actionlint then zizmor loop — actionlint for syntax, expression typing, and shellcheck of run steps; zizmor for security audits (expression injection, pullrequesttarget risks, unpinned actions, over-broad permissions). Use after editing any…
android-kotlin-compose
Android development with Kotlin and Jetpack Compose. Use when user mentions "Compose", "Jetpack Compose", "Material3", "Hilt", "Room", "ViewModel", or needs to build Android UI, implement MVVM architecture, manage Compose state, or integrate Jetpack libraries (Navigation, Room, Hilt, ViewModel). Triggers on…