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 jschulte/claude-plugins --skill productionizegit clone --depth 1 https://github.com/jschulte/claude-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/jschulte/claude-plugins/productionize)<a href="https://agentmods.dev/skills/jschulte/claude-plugins/productionize"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/productionize/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/jschulte/claude-plugins/productionize"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/productionize.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 | $0.00034 | $0.02666 |
| Opus 5.5 | $0.00014 | $0.01066 |
| Sonnet 5.5 | $0.00007 | $0.00533 |
| Haiku 4.5 | $0.00003 | $0.00267 |
Grade A, and why
productionize 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 24d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
productionize — draft PR to reviewable PR
A draft PR is private scratch. Publishing it is the moment three things have to agree:
the diff, the prose that describes it, and the verification claims attached to it. Most
"ready for review" PRs fail because one of the three drifted — a body describing the
second commit, a ## Verified list nobody ran, a review thread answered in chat.
This skill closes that gap for one PR and hands a reviewer something approvable without archaeology.
The one-PR rule
Other sessions work other PRs on the same repo at the same time. Everything below is scoped to the target PR's own worktree.
- Never edit, stage, or commit in the user's main checkout.
- Never touch another worktree, or a branch that isn't this PR's head.
- Never
git stash,reset --hard,checkout -f, orcleananywhere you did not create. - Never rewrite history or force-push. Push is fast-forward only.
- One PR per invocation. When you finish, name the next PR — do not start it.
Phase 0 — Resolve the target
Resolve all six before touching anything. Print them as a block; the user sees what you locked onto before you act on it.
| How | |
|---|---|
| Repo + PR | Argument (87, #87, owner/repo#87, URL) or infer from the current branch |
| Host | Parse git remote get-url origin; export GH_HOST when it isn't github.com |
| Base | From the API. Never assume main — stacked PRs base on another branch |
| Head + head SHA | From the API. The SHA is your move-detection baseline for the whole run |
| Gate | Repo's own definition of done, else a definition-of-done skill if one is installed, else references/gate.md |
| Verification commands | Only scripts/targets that actually exist in this repo |
The gate file lives on the PR's tree, not yours. Read it with
git show origin/<head>:<path>, not from the working directory — the branch you are
publishing may be the branch that introduces or changes the gate. Reading the local copy
gates the PR against a standard from some other branch, and nothing about the output
looks wrong.
What ships with it
2 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.
- 24d ago First seen · 215 lines · 34 tokens per session scan A 2c81855c08ab
productionize is a skill published in the GitHub repository jschulte/claude-plugins (0 stars, last pushed 25d ago), licensed MIT. It adds 34 tokens to every session and 2,666 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 2026-10-12.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
hero-diff-highlight
A dark code editor reveals a red deletion then a green addition with a soft pulse. Function: PR / code-change explainer.
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify unnecessary surface area before commit.