Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/perniemann/pnCorenpx agentmods add skills/perniemann/pncore/pn-slice-contractsWrote 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-slice-contracts)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-slice-contracts"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-slice-contracts/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-slice-contracts"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-slice-contracts.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 | $0.00056 | $0.01763 |
| Opus 5 | $0.00028 | $0.00881 |
| Sonnet 5 | $0.00011 | $0.00353 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
pn-slice-contracts 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 9d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slice contracts
When used as a standalone skill, begin every response with [pn-skill] 🔺
When to use
Use this skill at feature_program step 1 to define and lock interface contracts between slices, and to generate .cursor/worktrees.json. Also use at step 4 (verifier gate) to author contract-conformance tests and interpret verifier reports.
Purpose
Contracts are the seams between slices. They must be locked before fan-out so every slice works against the same interface. Without locked contracts, parallel agents invent incompatible field names (userId vs user_id vs uid) and the merge phase becomes a semantic debugging session.
Contract types and when to use each
| Type | When | Example |
|---|---|---|
| TypeScript interfaces | Shared data models, request/response shapes in a TS monorepo | interface CreateOrderRequest { userId: string; items: OrderItem[] } |
| JSON Schema | Language-agnostic APIs, config files, event envelopes | { "type": "object", "properties": { "userId": { "type": "string" } } } |
| OpenAPI stubs | REST endpoints consumed across slices | paths: /orders: post: requestBody: ... |
| GraphQL schema fragment | Shared types in a GraphQL API | type Order { id: ID! userId: ID! items: [OrderItem!]! } |
Use the simplest format that covers the consuming slice's needs. TypeScript interfaces for all-TS repos; OpenAPI stubs when contracts cross language boundaries.
Where contracts live
docs/refs/contracts/<programSlug>/
├── shared-types.ts ← TypeScript shared interfaces
├── api-stubs.yaml ← OpenAPI stubs (paths only, no implementation)
├── events.schema.json ← JSON Schema for event envelopes
└── README.md ← Contract index (auto-generated at step 1)
Rules:
- All contract files live in
docs/refs/contracts/<programSlug>/. - Contract files are read-only to slice worktrees — slices consume but do not edit them.
- Any edit to contracts re-triggers step 1 review (major patch path).
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.
- 9d ago First seen · 181 lines · 56 tokens per session scan A 11e97ac611b9
pn-slice-contracts is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 6d ago), licensed MIT. It adds 56 tokens to every session and 1,763 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
t-800-run-gates
A set of machine checks for deciding whether a T-800 run is ready to finish. It covers different run modes, such as creating, patching, looping, or auditing.
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
web3-testing
Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking. Use when testing Solidity contracts, setting up blockchain test suites, or validating DeFi protocols.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
implement-universal
Harness-agnostic version of /implement. Drives a single workshop ticket through the SWE→Tester loop in ONE conversation, with the role prompts bundled as agents/software-engineer.md and agents/tester.md instead of being launched as subagents. Resolves the ticket from implementyourself/tasks/, creates an…
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.