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 narumiruna/pi-extensions --skill typesafe-aigit clone --depth 1 https://github.com/narumiruna/pi-extensionsWrote 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/narumiruna/pi-extensions/typesafe-ai)<a href="https://agentmods.dev/skills/narumiruna/pi-extensions/typesafe-ai"><img src="https://agentmods.dev/badge/skills/narumiruna/pi-extensions/typesafe-ai/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/narumiruna/pi-extensions/typesafe-ai"><img src="https://agentmods.dev/badge/skills/narumiruna/pi-extensions/typesafe-ai.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 | $0.00098 | $0.01629 |
| Opus 5.5 | $0.00039 | $0.00652 |
| Sonnet 5.5 | $0.00020 | $0.00326 |
| Haiku 4.5 | $0.00010 | $0.00163 |
Grade A, and why
typesafe-ai 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 26d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build with TypeSafe
TypeSafe makes units of AI intelligence usable like programming primitives: small judgments that code can compose into larger capabilities. Its System One models return focused typed judgments and probabilities instead of prose or reasoning explanations. Jev is TypeSafe's flagship System One model. Keep workflow, policy, exact calculations, permissions, and side effects in code.
Read the bundled references
The bundled TypeSafe references are local snapshots for task use. The live TypeSafe documentation remains authoritative when freshness matters.
- Start with the reference index, then load only the files relevant to the task.
- Read System One and workflow concepts before deciding whether TypeSafe fits a new workflow.
- Read question design before composing Choice, Noul, or Score questions.
- Read composition patterns when batching, combining signals, or gating actions.
- For an integration, read the matching HTTP API, Python SDK, or JavaScript SDK reference.
- For an older integration, read the v1 migration guide before changing request or response shapes.
- For a new workflow, inspect the closest cookbook: routing and extraction, retrieval and classification, or verification and learning.
- If a snapshot appears stale or omits a needed detail, consult the upstream source recorded in the index or the installed SDK types.
- State any access limitation and do not invent version-dependent fields, limits, retries, or model behavior.
Use typesafe_question
When the typesafe_question tool is active, prefer it for direct Jev judgments instead of constructing an HTTP request manually.
Read its active schema before the first call because the tool validates each primitive's request shape.
Supply one shared state and a non-empty map of named questions.
Do not add provider credentials, endpoints, or model fields to tool input.
The extension prefers the official TypeSafe API when TYPESAFE_API_KEY is available and uses its experimental OpenRouter fallback only when openRouterFallback: true in the package-owned pi-typesafe.json settings file explicitly enables it.
A provider failure is not a reason to change a valid question or silently switch workflows.
What ships with it
12 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.
- LICENSE 1.0 KB
- references/api/http.md 4.1 KB
- references/api/migration-v1.md 3.4 KB
- references/composition-patterns.md 4.3 KB
- references/concepts.md 5.8 KB
- references/cookbooks/retrieval-and-classification.md 4.0 KB
- references/cookbooks/routing-and-extraction.md 5.0 KB
- references/cookbooks/verification-and-learning.md 4.7 KB
- references/index.md 3.5 KB
- references/question-design.md 6.3 KB
- references/sdk/javascript.md 1.9 KB
- references/sdk/python.md 3.2 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.
- 26d ago First seen · 118 lines · 98 tokens per session scan A 7fb988672c4b
typesafe-ai is a skill published in the GitHub repository narumiruna/pi-extensions (693 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 1,629 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 2026-09-20.
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.
ax-gen
This skill helps an LLM generate correct AxGen code using @ax-llm/ax. Use when the user asks about ax(), AxGen, generators, forward(), streamingForward(), validation, assertions, streaming assertions, field processors, step hooks, self-tuning, or structured outputs. For MCP clients, transports, prompts, resources…
ax-signature
This skill helps an LLM generate correct DSPy signature code using @ax-llm/ax. Use when the user asks about signatures, s(), f(), field types, string syntax, fluent builder API, validation constraints, or type-safe inputs/outputs.
ax-llm
This skill helps with using the @ax-llm/ax TypeScript library for building LLM applications. Use when the user asks about ax(), ai(), f(), s(), agent(), flow(), AxGen, AxAgent, AxFlow, signatures, streaming, or mentions @ax-llm/ax.
ax-playbook
This skill helps an LLM generate correct playbook code using @ax-llm/ax. Use when the user asks about playbook(), AxPlaybook, context playbooks, evolving context, ACE / Agentic Context Engineering, agent.playbook(), or growing/applying task knowledge offline and online with evolve() and update().
ax-refine
Use this skill when writing or reviewing Ax bestOfN/refine code, reward functions, thresholds, native sample selection, serial attempts, generated advice, and attempt diagnostics.