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-monorepogit 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-monorepo)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-monorepo"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-monorepo/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/perniemann/pncore/pn-monorepo"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-monorepo.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 | $0.00052 | $0.00757 |
| Opus 5.5 | $0.00021 | $0.00303 |
| Sonnet 5.5 | $0.00010 | $0.00151 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
pn-monorepo 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 1mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monorepo
This SKILL.md is a router; load reference.md only when that workflow is active.
When to use
- Setting up a new monorepo with Turborepo, Nx, or pnpm workspaces
- Adding a new package or app to an existing monorepo
- Configuring build caching and task pipelines
- Publishing shared packages (
publishConfig, changesets) - Diagnosing slow builds or dependency resolution issues
- Migrating a multi-repo project into a monorepo
For full config files, package.json examples, and CI setup, see reference.md.
Tool decision matrix
| Tool | When to prefer |
|---|---|
| Turborepo | Simple task orchestration, JS/TS focused, minimal config, Vercel deployment |
| Nx | Large monorepos, cross-language, plugin ecosystem, IDE integration |
| pnpm workspaces (standalone) | Lightweight setups where you only need workspace linking |
| Nx + pnpm | Large teams with complex graph, best cache and affected analysis |
| Turborepo + pnpm | Most common 2026 default for JS/TS stacks |
Structure
my-monorepo/
├── apps/
│ ├── web/ (Next.js)
│ └── api/ (Node.js / Hono)
├── packages/
│ ├── ui/ (shared React components)
│ ├── config-ts/ (shared tsconfig)
│ └── utils/ (shared utilities)
├── turbo.json
├── package.json
└── pnpm-workspace.yaml
Key rules
Shared tsconfig: Keep a base config-ts/base.json; each app extends it. Shared internal packages point exports directly to ./src/index.ts for zero-build dev.
Publishable packages: Set "private": false with publishConfig, exports, and files: ["dist"]. Build with tsup.
Internal packages: Set "private": true, exports to ./src/index.ts. Consuming apps declare "@my-org/utils": "workspace:*".
Changesets: Use npx changeset add per PR, npx changeset version to bump, npx changeset publish to release.
Remote caching: Connect to Vercel remote cache or self-host with TURBO_API + TURBO_TOKEN.
What ships with it
1 file 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.
- 1mo ago Changed · +2 lines 0422d00e8235
- 1mo ago First seen · 69 lines · 52 tokens per session scan A 4efaad642643
pn-monorepo is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 757 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
t-800-plugin-sync
A procedural checklist for installing or synchronising the T-800 plugin in Cursor, including checking for outdated content and reloading the editor.
configure-workspaces
Propose and generate workspace configuration files (.humanlayer/workspace.json and .humanlayer/workspace.local.json) for a repository.
resolve-inputs
Select the Resolve mode, recover its input, check the workspace, and discover existing fixes.
feature-publish
Commit the feature, write the PR body, publish in the selected mode, and drive the PR.
otto-review-remediation
Handle trusted reviewers' change requests on Otto PRs.
feature-inputs
Read the input and ticket, choose the mode, run preflight, and check for existing delivery.