# Tool Authoring

> Use when creating, modifying, reviewing, or debugging Theseus Tool primitives or concrete tools in packages/theseus-core/src/tool and packages/theseus-tools.

- **Type:** Skill
- **Install:** `agentstack add skill-theseus-run-theseus-tool-authoring`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [theseus-run](https://agentstack.voostack.com/s/theseus-run)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [theseus-run](https://github.com/theseus-run)
- **Source:** https://github.com/theseus-run/theseus/tree/master/.agents/skills/tool-authoring
- **Website:** https://www.theseus.run

## Install

```sh
agentstack add skill-theseus-run-theseus-tool-authoring
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Tool Authoring

Use this skill for `Tool` primitive work and concrete tools.

## Read First

- `packages/theseus-core/src/Tool.ts`
- `packages/theseus-core/src/tool/index.ts`
- `packages/theseus-core/src/tool/run.ts`
- For concrete tools: the relevant file in `packages/theseus-tools/src/`

## Contract

A tool is typed world access for the model. It declares input, output, known failure, execution, presentation, and interaction policy.

Preserve this pipeline:

1. Decode raw model args with `tool.input`.
2. Run `tool.execute`, applying `tool.retry` if present.
3. Validate success output with `tool.output`.
4. Validate known failure with `tool.failure`.
5. Present success or known failure as `Presentation`.
6. Convert defects into `ToolDefect`.

Known failures are tool-result content for the model, not runtime exceptions. Runtime errors are decode, output-shape, failure-shape, and defect errors.

## Authoring Rules

- Use `Tool.defineTool`; do not create ad hoc tool objects unless testing a boundary directly.
- Use Effect Schema for `input`, `output`, and `failure`.
- Use `Tool.Defaults.NoFailure` only when the tool has no declared domain failure.
- Keep tool names stable and LLM-callable.
- Keep descriptions operational: what the tool does, not implementation trivia.
- Set `policy.interaction` intentionally. Do not default write-like behavior to observe/read semantics.
- If a tool touches the filesystem, shell, network, or process state, model that risk in policy and failure shape.
- Prefer small concrete tools over a generic "do anything" tool.

## Verification

- Run the package-local test when changing `packages/theseus-tools`: `bun test src/` from that package or root `bun run test` when impact crosses packages.
- Run root `bun run typecheck` when signatures, schemas, exports, or Effect environments change.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [theseus-run](https://github.com/theseus-run)
- **Source:** [theseus-run/theseus](https://github.com/theseus-run/theseus)
- **License:** MIT
- **Homepage:** https://www.theseus.run

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-theseus-run-theseus-tool-authoring
- Seller: https://agentstack.voostack.com/s/theseus-run
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.