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 pantheon-org/tekhne --skill practicesgit clone --depth 1 https://github.com/pantheon-org/tekhneWrote 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/pantheon-org/tekhne/practices)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/practices"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/practices/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/pantheon-org/tekhne/practices"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/practices.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 | $0.00106 | $0.01300 |
| Opus 5.5 | $0.00042 | $0.00520 |
| Sonnet 5.5 | $0.00021 | $0.00260 |
| Haiku 4.5 | $0.00011 | $0.00130 |
Grade A, and why
typescript-advanced-practices 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeScript Practices
Workflow-level habits: design types first, make bad states impossible to construct, validate at the boundary where untyped data enters, and organize modules so the type-first discipline stays easy to keep up.
Mindset
Design the types before writing the implementation — a type is a specification the compiler checks on every subsequent change, and writing it first forces the impossible states question to be answered up front rather than discovered later as a bug. An interface with many optional fields is usually a discriminated union that hasn't been modeled yet: if data and error can theoretically both be set, that combination will eventually occur, and the fix is a type that excludes it, not a runtime check that catches it after the fact. Runtime validation belongs at the boundary — the one place untyped data (an API response, form input, an environment variable) enters the typed world — not scattered through the code that consumes it; validate once there, and let the type system carry the guarantee everywhere downstream.
When to Apply
Use this skill when:
- Starting a new feature and deciding what the types should look like before writing implementation
- Spotting an interface with many optional fields that allow an impossible combination to compile
- Validating data at a system boundary (API responses, form input, environment variables) with Zod
- Deciding how to organize a module's exports (single-function modules, barrel files, internal encapsulation)
Use When
- "Where do I even start typing this feature?"
- "This interface has five optional fields — some combinations don't make sense. How do I fix that?"
- "How do I validate this API response is actually shaped the way I expect?"
- "Should this be one big module or several small ones?"
Scope
In Scope
- Type-first development workflow.
- Making illegal states unrepresentable with discriminated unions.
- Runtime validation with Zod at system boundaries.
- Module organization patterns (single-function modules, barrel exports, encapsulation).
What ships with it
18 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.
- .audits/2026-09-23/Analysis.md 494 B
- .audits/2026-09-23/audit.json 556 B
- .audits/2026-09-23/Remediation.md 1.4 KB
- evals/instructions.json 2.0 KB
- evals/scenario-0/capability.txt 141 B
- evals/scenario-0/criteria.json 1.1 KB
- evals/scenario-0/task.md 1.3 KB
- evals/scenario-1/capability.txt 154 B
- evals/scenario-1/criteria.json 1.3 KB
- evals/scenario-1/task.md 1.9 KB
- evals/scenario-2/capability.txt 160 B
- evals/scenario-2/criteria.json 1.1 KB
- evals/scenario-2/task.md 1.4 KB
- evals/summary.json 536 B
- references/illegal-states.md 5.8 KB
- references/module-patterns.md 5.5 KB
- references/runtime-validation.md 4.8 KB
- references/type-first.md 3.1 KB
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 · 149 lines · 106 tokens per session scan A 90dd5c1e4307
typescript-advanced-practices is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 106 tokens to every session and 1,300 once invoked, about $0.0004 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 2026-09-24.
Other skills, from other repositories
developing-genkit-js
Develop AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript/TypeScript, or when encountering Genkit errors, validation issues, type errors, or API problems.
antfu
Anthony Fu's opinionated tooling and conventions for JavaScript/TypeScript projects. Use when setting up new projects, configuring ESLint/Prettier alternatives, monorepos, library publishing, or when the user mentions Anthony Fu's preferences.
setup-ts-deep-modules
A setup for TypeScript packages that hides their implementation behind files at the package root. Dependency-cruiser checks that outside code uses these entry points, prevents dependency cycles, and keeps internal folders private.
aws-lambda-typescript-integration
Provides AWS Lambda integration patterns for TypeScript with cold start optimization. Use when creating or deploying TypeScript Lambda functions, choosing between NestJS framework and raw TypeScript approaches, optimizing cold starts, configuring API Gateway or ALB integration, or implementing serverless TypeScript…
loom-typescript
TypeScript language expertise for type-safe, production-quality code.
senior-frontend
Frontend development for React 19, Next.js 15, TypeScript, and Tailwind CSS v4 / Pengembangan frontend dengan React 19, Next.js 15, TypeScript, dan Tailwind CSS v4.