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/transloadit/node-sdk/gh-pr-to-greennpx skills add transloadit/node-sdk --skill gh-pr-to-greengit clone --depth 1 https://github.com/transloadit/node-sdkWrote 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/transloadit/node-sdk/gh-pr-to-green)<a href="https://agentmods.dev/skills/transloadit/node-sdk/gh-pr-to-green"><img src="https://agentmods.dev/badge/skills/transloadit/node-sdk/gh-pr-to-green.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 | $0.00082 | $0.00500 |
| Opus 5 | $0.00041 | $0.00250 |
| Sonnet 5 | $0.00016 | $0.00100 |
| Haiku 4.5 | $0.00008 | $0.00050 |
Grade A, and why
gh-pr-to-green scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
GH PR to Green
Workflow
- Get context from PR with
gh; make sure all review comments, threads, CI failures, and PR description updates are included. - Write them as a markdown todolist in
repodocs/prompts/${YYYY}-${MM}-${DD}-${sluggedSemanticTopic}.mdand commit it. If therepodocs/prompts/dir does not exist, use thedocs/prompts/dir. - Merge the latest main into our branch and resolve any conflict carefully.
- Determine which review items are correct.
- Keep working until all items are checked off, either by fixing the issue, or explaining why not in the markdown list as well as comments in code where applicable/sensible.
- Commit and push.
- Invoke
council-review - If the PR has UI/UX impact, invoke
claude-usertestinstead of duplicating browser-test instructions here. Treat its output as reviewer input, reconcile findings yourself, and fold valid fixes back into this PR-to-green loop. - Run the repo-required checks (often
yarn check). - Fix any issue that you deem related and worth fixing.
- Commit and push.
- Monitor CI until green:
- Prefer
gh run watch(works everywhere withgh). - If
gh-run-watch.tsexists in the repo, it's fine to use that too.
- Prefer
- Fix any issue that you deem related and worth fixing.
- Rinse and repeat until CI is green, or there are only 100% unrelated issues remaining.
This skill is PR orchestration only. Do not add inline UX/browser/user-test instructions here; use dedicated validation skills for those workflows.
Report back with a list of all changes made, and offer a link to the PR for inspection and merge.
Offer to squash merge with --admin if the human thinks a last manual review is not needed.
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.
- 5d ago First seen · 42 lines · 82 tokens per session scan A d5f9ec368dd9
gh-pr-to-green is a skill published in the GitHub repository transloadit/node-sdk (73 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 500 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
provable-sdk-tutorial-docs
Use when writing tutorial documentation or create-leo-app examples for the Provable SDK (@provablehq/sdk). Covers how to structure runnable templates, write tutorial-style docs, and handle Node.js vs web runtime differences.
commerce-js-integration
Build a lightweight headless store using the Commerce.js SDK for product display, cart management, and checkout without a heavy backend.
release-ts-sdk
Use when cutting a release of @aptos-labs/ts-sdk or @aptos-labs/confidential-asset. Phase 1 bumps the version, stamps the changelog, and opens the release PR. Phase 2 (after the PR merges to main) cuts the tag and GitHub Release that triggers the NPM publish workflow.
lint-js
Lint JS/TS code only. Use before opening a PR when only JavaScript or TypeScript files were changed (no Rust).
git-cleanup
Clean up local git branches and remotes accumulated from PR reviews. Use when the user asks to clean branches, remove stale remotes, or tidy up the local git state.
Shade dropdown surface contract
DropdownMenu, Select, and Popover share one visual recipe (bg-surface-elevated-2 + border-border/60 dark:border-border/30 + shadow-md). Change them together. Trigger when editing any of those three Shade files.