How do I install the Goose Foundation skill?

Run npx skillmds@latest add ryan-brosas/goose-foundation in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Goose Foundation safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Goose Foundation?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Goose Foundation free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Goose Foundation?

ryan-brosas (@ryan-brosas) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Goose Foundation by ryan-brosas — Agent Skill

Name: Goose Foundation
Author: ryan-brosas

Goose Foundation

Use when porting Block's goose AI-agent provider machinery — provider trait + collect_stream fold kernel, sanitized/migrating conversation model, audience projection, bounded think-tag stream filter, thinking-effort negotiation, declarative prompt-cache semantics, fail-safe NDJSON request logging, RFC 8628 device flows, typed provider error taxonomy, retry/backoff ladder, transient-only gating, formats/* payload-mapping layer (Anthropic request/SSE fold, OpenAI chat replay coherence + stream triage, Databricks dual-dialect dispatch, Google thought-signature continuity, thinking-config table, OpenAI Responses input mapper + typed-event stream fold, Ollama XML tool-call fallback), declarative provider plane (JSON-defined engine factory, env-expanded base URLs, thin OpenAI-compatible client, completions-prefix composition, tri-effect non-streaming mode, /models failure classification, static-list fallback gate).

ryan-brosas Updated Sep 17, 2026

File contents

goose: AI-Agent Provider Foundation

Foundation contract

This is a cold, source-specific foundation, not an operational procedure. It is historical, revision-pinned evidence rather than timeless guidance. Current project source, tests, requirements, and runtime behavior outrank this projection and decide what ships.

Provenance and revision

Source record: goose; portable upstream identity, license, coverage caveats, and retrieval history are preserved in the index.
Recorded revision: main@2eb3ab1001dedb5ab09a6ed60158adfc248bac56.
Full provenance, coverage caveats, boundaries, and preserved evidence: references/index.md.

Topic map

Representative topics: Retry/backoff ladder; Provider error taxonomy; Provider trait + stream fold; Sanitized message model; Think-tag stream filter; Thinking-effort negotiation; Prompt-cache semantics; Request logger SPI.
Scope and retrieval questions: references/index.md#use-this-for.
Complete capsule chooser: references/index.md#load-the-matching-source-dump.
Detailed grouped map: references/index.md#capsule-map.
Source limitations and portability boundaries: references/index.md#boundaries.

Retrieval

Open the index, choose one capsule matching the active question, and load only that capsule. Revalidate its cited source and revision before relying on it. Do not bulk-load the inventory, treat historical claims as current truth, or apply this foundation as a procedure.

---name: goose-foundationdescription: Use when porting Block's goose AI-agent provider machinery — provider trait + collect_stream fold kernel, sanitized/migrating conversation model, audience projection, bounded think-tag stream filter, thinking-effort negotiation, declarative prompt-cache semantics, fail-safe NDJSON request logging, RFC 8628 device flows, typed provider error taxonomy, retry/backoff ladder, transient-only gating, formats/* payload-mapping layer (Anthropic request/SSE fold, OpenAI chat replay coherence + stream triage, Databricks dual-dialect dispatch, Google thought-signature continuity, thinking-config table, OpenAI Responses input mapper + typed-event stream fold, Ollama XML tool-call fallback), declarative provider plane (JSON-defined engine factory, env-expanded base URLs, thin OpenAI-compatible client, completions-prefix composition, tri-effect non-streaming mode, /models failure classification, static-list fallback gate).---# goose: AI-Agent Provider Foundation## Foundation contractThis is a cold, source-specific foundation, not an operational procedure. It ishistorical, revision-pinned evidence rather than timeless guidance. Currentproject source, tests, requirements, and runtime behavior outrank thisprojection and decide what ships.## Provenance and revision- Source record: `goose`; portable upstream identity, license, coverage caveats, and retrieval history are preserved in the index.- Recorded revision: `main@2eb3ab1001dedb5ab09a6ed60158adfc248bac56`.- Full provenance, coverage caveats, boundaries, and preserved evidence: `references/index.md`.## Topic map- Representative topics: Retry/backoff ladder; Provider error taxonomy; Provider trait + stream fold; Sanitized message model; Think-tag stream filter; Thinking-effort negotiation; Prompt-cache semantics; Request logger SPI.- Scope and retrieval questions: `references/index.md#use-this-for`.- Complete capsule chooser: `references/index.md#load-the-matching-source-dump`.- Detailed grouped map: `references/index.md#capsule-map`.- Source limitations and portability boundaries: `references/index.md#boundaries`.## RetrievalOpen the index, choose one capsule matching the active question, and load onlythat capsule. Revalidate its cited source and revision before relying on it. Donot bulk-load the inventory, treat historical claims as current truth, or applythis foundation as a procedure.

Frequently asked questions