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 perniemann/pnCore --skill pn-ci-dev-prod-splitgit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/perniemann/pncore/pn-ci-dev-prod-split)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-ci-dev-prod-split"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-ci-dev-prod-split.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 5.1 | $0.00055 | $0.00605 |
| Opus 5 | $0.00028 | $0.00302 |
| Sonnet 5 | $0.00011 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
pn-ci-dev-prod-split 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI dev/prod split
When to use
- Scaffolding CI for a new project
- Adding deploy workflows to an existing repo
- User asks for "dev and prod" or "staging vs production" CI
- Fixing or refactoring workflows that merge dev/prod in one file
Pattern
| Workflow | Trigger | Concurrency | Deploy target |
|---|---|---|---|
| deploy-dev | push to main (or develop), paths-ignore | cancel-in-progress: true | Dev path/env |
| deploy-prod | workflow_dispatch only | cancel-in-progress: false | Prod path/env |
| *-test (optional) | workflow_dispatch | — | Tests dev + prod connectivity |
Principles: Dev auto-deploys on push; prod is manual-only; separate env vars (e.g. PUBLIC_ENV=development vs production); separate paths/secrets (DEV_, PROD_).
Instructions
- Separate workflows: Create
deploy-dev.ymlanddeploy-prod.yml(not one workflow with branch condition). - Dev workflow: Trigger on push to main (or develop). Use paths-ignore for non-code changes (e.g. README, .cursorrules). Build with
PUBLIC_ENV=developmentor equivalent. - Prod workflow: Trigger on workflow_dispatch only. Never auto-deploy to prod. Build with
PUBLIC_ENV=productionor equivalent. Useenvironment: productionin GitHub for optional approval gates. - Concurrency: Dev:
cancel-in-progress: true(new push cancels in-flight deploy). Prod:cancel-in-progress: false(do not cancel prod deploy). - Deploy target adapters:
- FTP: DEV_FTP_PATH vs PROD_FTP_PATH; separate .htaccess (dev: password protect; prod: security headers)
- Vercel: Preview = dev; Production = prod; use env vars per environment
- Netlify: Branch deploys = dev; Production = prod
- Cloudflare Pages: Preview = dev; Production = prod
- Optional test workflow: Manual workflow to verify deploy connectivity (e.g. ftp-test for FTP) for both dev and prod paths.
- Reference pn-ci: For secrets (never in YAML), action pinning, caching. Keep workflows minimal.
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 · 44 lines · 55 tokens per session scan A 0a21856561b9
pn-ci-dev-prod-split is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 605 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
github-actions-templates
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
secrets-management
Implement secure secrets management for CI/CD pipelines using Vault, AWS Secrets Manager, or native platform solutions. Use when handling sensitive credentials, rotating secrets, or securing CI/CD environments.
deployment-pipeline-design
Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration. Use this skill when designing zero-downtime deployment pipelines, implementing canary rollout strategies, setting up multi-environment promotion workflows, or debugging failed deployment gates in CI/CD.
gitlab-ci-patterns
Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment.
nx-workspace-patterns
Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.
typescript
TypeScript coding conventions, best practices, and patterns for writing clean, maintainable code.