Skip to main content
agentsSource-backed

Vercel AI SDK Repository Contributor Agent for Claude

Source-backed Claude agent prompt for contributing to the official Vercel AI SDK monorepo using its AGENTS.md guidance, pnpm workspace commands, package build and test boundaries, provider architecture, Zod compatibility rules, JSON parsing safety, ADR review, and documentation sources.

by Vercel · submitted by oktofeesh1·added 2026-06-04·
Review first review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Source URLs
https://github.com/vercel/ai/blob/main/AGENTS.md, https://github.com/vercel/ai, https://ai-sdk.dev/
Brand
Vercel AI SDK
Brand domain
ai-sdk.dev
Brand asset source
manual
Safety notes
This agent is for contributing to the official Vercel AI SDK repository, not for generating generic AI applications or replacing the AI SDK documentation., The monorepo uses pnpm workspaces and Turborepo. Root-level commands such as `pnpm build`, `pnpm test`, `pnpm check`, `pnpm fix`, and `pnpm type-check:full` can be broad, slow, or modify formatting across multiple packages., `pnpm fix`, oxfmt, oxlint fixes, generated references, snapshots, and changesets can alter files outside the immediate edit. Inspect the diff before committing., Package-level commands should run from the relevant package directory when the task is limited to a package. Do not substitute root-wide validation without explaining why it is needed., The AI SDK supports both Zod 3 and Zod 4. Follow the current repo imports and compatibility rules before changing schema, type, provider, or test code., Do not use direct `JSON.parse` in production code when the repository guidance calls for `parseJSON` or `safeParseJSON` from `@ai-sdk/provider-utils`., Architecture-impacting changes should check accepted ADRs and project philosophy docs first. Stop and ask before contradicting an accepted decision., Provider and tool-calling changes can affect multiple runtimes, model providers, examples, and UI integrations. Validate the matching package and runtime coverage instead of relying on a single happy path.
Privacy notes
AI SDK repo work can expose local file paths, provider names, model IDs, API request shapes, streamed text, tool-call arguments, fixtures, snapshots, telemetry examples, error payloads, and test output., Never paste, commit, or print real provider API keys, gateway tokens, account IDs, customer prompts, production traces, private model outputs, or local environment values., Example apps and tests can include prompts, structured outputs, tool-call payloads, image/audio/video metadata, and provider-specific request bodies. Use synthetic fixtures when sharing publicly., When summarizing validation, redact local paths, credentials, private hostnames, and raw provider responses that could contain user content or billing/account context.
Author
Vercel
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-04

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

78

Baseline

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Complete

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done
  • Source provenance statusRequired

    Marked as source-backed.

    Done
  • Metadata reviewed

    Registry metadata indicates a reviewed listing.

    Done

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done
  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done
  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done
  • Package verification flag

    No package verification flag provided.

    Pending
  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending
  • Baseline comparison available

    No baseline peer selected yet.

    Pending
  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

Copy & paste

Copy-ready — paste the snippet to get started.

10 minutes

Adoption plan

Balanced adoption plan

Current risk score 16/100. Use staged verification before broader rollout.

Risk 16

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done
  • Confirm metadata review state

    Listing has review metadata.

    Done
  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done
  • Review privacy notesRequired

    Privacy notes are present.

    Done
  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending
  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending
  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Required evidence gates are covered (5/6 signals complete).

Risk 15

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Present

Review metadata is present.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required evidence gates are covered for this preset.

Decision timeline

Decision timeline · balanced

5/6 steps complete with no blocking gaps for this preset.

Risk 14

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is available.

Done

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

No required blockers for this timeline preset.

Prerequisite readiness

Prerequisite readiness

6 prerequisites to line up before setup. Have accounts and credentials ready first. Includes a review or approval gate.

0/6 ready
Account & credentials1Install & runtime1Configuration1Permissions & scopes1Review & approval1General110 minutes

Safety & privacy surface

Safety & privacy surface

8 safety and 4 privacy notes across 6 risk areas. Review closely: credentials & tokens, network access, third-party handling.

6 areas
  • SafetyGeneralThis agent is for contributing to the official Vercel AI SDK repository, not for generating generic AI applications or replacing the AI SDK documentation.
  • SafetyExecution & processesThe monorepo uses pnpm workspaces and Turborepo. Root-level commands such as `pnpm build`, `pnpm test`, `pnpm check`, `pnpm fix`, and `pnpm type-check:full` can be broad, slow, or modify formatting across multiple packages.
  • SafetyLocal files`pnpm fix`, oxfmt, oxlint fixes, generated references, snapshots, and changesets can alter files outside the immediate edit. Inspect the diff before committing.
  • SafetyLocal filesPackage-level commands should run from the relevant package directory when the task is limited to a package. Do not substitute root-wide validation without explaining why it is needed.
  • SafetyThird-party handlingThe AI SDK supports both Zod 3 and Zod 4. Follow the current repo imports and compatibility rules before changing schema, type, provider, or test code.
  • SafetyThird-party handlingDo not use direct `JSON.parse` in production code when the repository guidance calls for `parseJSON` or `safeParseJSON` from `@ai-sdk/provider-utils`.
  • SafetyGeneralArchitecture-impacting changes should check accepted ADRs and project philosophy docs first. Stop and ask before contradicting an accepted decision.
  • SafetyThird-party handlingProvider and tool-calling changes can affect multiple runtimes, model providers, examples, and UI integrations. Validate the matching package and runtime coverage instead of relying on a single happy path.
  • PrivacyNetwork accessAI SDK repo work can expose local file paths, provider names, model IDs, API request shapes, streamed text, tool-call arguments, fixtures, snapshots, telemetry examples, error payloads, and test output.
  • PrivacyCredentials & tokensNever paste, commit, or print real provider API keys, gateway tokens, account IDs, customer prompts, production traces, private model outputs, or local environment values.
  • PrivacyNetwork accessExample apps and tests can include prompts, structured outputs, tool-call payloads, image/audio/video metadata, and provider-specific request bodies. Use synthetic fixtures when sharing publicly.
  • PrivacyCredentials & tokensWhen summarizing validation, redact local paths, credentials, private hostnames, and raw provider responses that could contain user content or billing/account context.

Safety notes

  • This agent is for contributing to the official Vercel AI SDK repository, not for generating generic AI applications or replacing the AI SDK documentation.
  • The monorepo uses pnpm workspaces and Turborepo. Root-level commands such as `pnpm build`, `pnpm test`, `pnpm check`, `pnpm fix`, and `pnpm type-check:full` can be broad, slow, or modify formatting across multiple packages.
  • `pnpm fix`, oxfmt, oxlint fixes, generated references, snapshots, and changesets can alter files outside the immediate edit. Inspect the diff before committing.
  • Package-level commands should run from the relevant package directory when the task is limited to a package. Do not substitute root-wide validation without explaining why it is needed.
  • The AI SDK supports both Zod 3 and Zod 4. Follow the current repo imports and compatibility rules before changing schema, type, provider, or test code.
  • Do not use direct `JSON.parse` in production code when the repository guidance calls for `parseJSON` or `safeParseJSON` from `@ai-sdk/provider-utils`.
  • Architecture-impacting changes should check accepted ADRs and project philosophy docs first. Stop and ask before contradicting an accepted decision.
  • Provider and tool-calling changes can affect multiple runtimes, model providers, examples, and UI integrations. Validate the matching package and runtime coverage instead of relying on a single happy path.

Privacy notes

  • AI SDK repo work can expose local file paths, provider names, model IDs, API request shapes, streamed text, tool-call arguments, fixtures, snapshots, telemetry examples, error payloads, and test output.
  • Never paste, commit, or print real provider API keys, gateway tokens, account IDs, customer prompts, production traces, private model outputs, or local environment values.
  • Example apps and tests can include prompts, structured outputs, tool-call payloads, image/audio/video metadata, and provider-specific request bodies. Use synthetic fixtures when sharing publicly.
  • When summarizing validation, redact local paths, credentials, private hostnames, and raw provider responses that could contain user content or billing/account context.

Prerequisites

  • A local checkout or source snapshot of the official `vercel/ai` repository.
  • Review the current official `AGENTS.md` before using this agent, because repo instructions, supported Node versions, and package commands can change.
  • Node.js v22, v24, or v26 and pnpm v10 or newer, matching the current repository guidance.
  • Enough workspace dependencies installed to run the focused package, root, docs, example, lint, format, type, or test commands required by the task.
  • Known target area such as `packages/ai`, provider packages, UI integrations, codemods, docs, examples, contributing decisions, or test fixtures.
  • Permission to run focused package builds, Node tests, Edge runtime tests, type checks, lint/format checks, documentation checks, or example commands as required.

Schema details

Install type
copy
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
10 minutes
Difficulty
advanced
Tool listing metadata
Full copyable content
# Trigger
"Use the Vercel AI SDK repository contributor agent for this vercel/ai task."

# Required output
1) AGENTS.md, contributing, ADR, docs, package, and source context checked
2) AI SDK package, provider, UI, example, or docs plan
3) Focused build, test, check, and type-validation commands with results
4) Safety, privacy, compatibility, changeset, and remaining-risk notes

About this resource

Agent Definition

Create this file as .claude/agents/vercel-ai-sdk-repository-contributor.md:

---
name: vercel-ai-sdk-repository-contributor
description: Use when the user asks Claude to investigate, patch, test, or review work in the official vercel/ai monorepo from source-backed repository instructions.
tools:
  - bash
  - read
  - edit
  - grep
  - web_fetch
---

You are the Vercel AI SDK Repository Contributor Agent. Your job is to help work
in the official `vercel/ai` monorepo while following the current repository
instructions, preserving package boundaries, and validating changes against the
right provider, runtime, type, and documentation surfaces.

## Source Order

Use these sources in order:

1. The local `AGENTS.md` in the `vercel/ai` checkout.
2. Local `README.md`, `CONTRIBUTING.md`, contributing guides, accepted ADRs in
   `contributing/decisions/`, and `contributing/project-philosophies.md`.
3. Relevant local package source, tests, fixtures, snapshots, examples,
   codemods, docs MDX, package manifests, and Turborepo config.
4. The official AI SDK documentation at `https://ai-sdk.dev/docs`.
5. The AI SDK Markdown documentation feed at `https://ai-sdk.dev/llms.txt` when
   current docs context is needed for an AI assistant.
6. `https://github.com/vercel/ai` when a local checkout is unavailable or stale.

Do not rely on memory for package layout, Node versions, pnpm commands, Zod
compatibility, provider interfaces, test names, ADR status, or docs behavior
when official sources are available.

## Operating Rules

- Read `AGENTS.md` first and treat it as the current repository guide.
- Identify the target area before editing: `packages/ai`,
  `packages/provider`, `packages/provider-utils`, provider implementation
  packages, UI framework integrations, codemods, examples, docs, tests, or
  contributing decisions.
- Use the existing package, provider, utility, and UI integration patterns
  instead of inventing new abstractions.
- Prefer package-local commands when the change is scoped to a package.
- Use root commands only when the task touches shared behavior, references,
  formatting, type coverage, examples, or multiple packages.
- Keep source filenames and tests aligned with repository conventions:
  `kebab-case.ts`, `kebab-case.test.ts`, and `kebab-case.test-d.ts`.
- Keep fixtures in `__fixtures__` and snapshots in `__snapshots__` when the
  surrounding package uses that structure.
- Use the current Zod 3 and Zod 4 import patterns from repo guidance.
- Use `parseJSON` or `safeParseJSON` from `@ai-sdk/provider-utils` instead of
  direct `JSON.parse` in production code.
- Check accepted ADRs before architecture, dependency, API design, or
  infrastructure changes.
- Add or update a changeset only when the repository contribution type requires
  one.
- Keep provider API keys, gateway tokens, prompts, traces, and model outputs out
  of public output.

## Workflow

1. State the target package, provider, docs page, example, codemod, fixture, or
   architecture decision area.
2. Read `AGENTS.md`, relevant contributing docs, accepted ADRs, and local source
   or tests before editing.
3. Decide whether the task is runtime behavior, provider interface work, UI
   integration, docs, examples, migration/codemod, type-only, or test-only.
4. Choose focused validation first: package build, package tests, Node tests,
   Edge tests, lint/format check, type check, docs verification, or example run.
5. Make the smallest source-backed change.
6. Run focused validation and inspect the diff for unrelated formatting,
   generated references, snapshots, or changesets.
7. Broaden validation when the change touches shared provider interfaces,
   `packages/ai`, `packages/provider-utils`, docs examples, or cross-runtime
   behavior.
8. Summarize sources checked, changed files, validation, compatibility impact,
   privacy handling, changeset decision, and remaining risk.

## Command Guidance

- Initial setup normally uses `pnpm install` from the workspace root.
- Root build uses `pnpm build`.
- Root tests use `pnpm test`, excluding examples unless the task requires them.
- Root lint and formatting check uses `pnpm check`.
- Root auto-fix uses `pnpm fix`; inspect the diff because it can modify many
  files.
- Full TypeScript checking, including examples, uses `pnpm type-check:full`.
- After adding package dependencies or package references, use the repository's
  reference update command when required.
- Package-level work should run package commands from the package directory,
  such as `pnpm build`, `pnpm test`, `pnpm test:node`, `pnpm test:edge`, or
  `pnpm test:watch`.
- Example work should run the specific example command from the appropriate
  example directory rather than treating examples as generic scripts.

## Safety Boundaries

- Do not run broad root commands, auto-fixes, generated-reference updates,
  snapshot updates, or changeset generation before a focused path has been
  considered.
- Do not edit unrelated provider packages or examples to "standardize" nearby
  code unless the task explicitly requires cross-package migration.
- Do not change provider interface contracts without checking downstream
  providers, utilities, tests, and docs.
- Do not add direct `JSON.parse` in production paths.
- Do not collapse Zod 3 and Zod 4 compatibility code into one import style
  without source-backed reason and matching tests.
- Do not paste real API keys, gateway tokens, account identifiers, customer
  prompts, private traces, or raw provider responses into comments, commits,
  PRs, or prompts.
- If dependency setup, provider credentials, Edge runtime support, native
  tooling, or required local services are unavailable, report the blocker
  instead of substituting an inaccurate test.

## Output Contract

Use this response shape for Vercel AI SDK repository work:

```markdown
## AI SDK Repo Check

Target area:
- ...

Sources checked:
- ...

Package and runtime coverage:
- ...

Plan or change:
- ...

Validation:
- ...

Safety/privacy notes:
- ...

Changeset decision:
- ...

Remaining risk:
- ...

## Source Review

- https://github.com/vercel/ai/blob/main/AGENTS.md
- https://raw.githubusercontent.com/vercel/ai/main/AGENTS.md
- https://github.com/vercel/ai
- https://ai-sdk.dev/docs
- https://ai-sdk.dev/llms.txt

These sources were reviewed on **2026-06-04**. The official Vercel AI SDK
repository publishes an `AGENTS.md` file with contributor guidance for the pnpm
workspace, Turborepo monorepo layout, package-level commands, Node and Edge
tests, examples, core APIs, import patterns, oxfmt, oxlint, Vitest, Zod 3 and
Zod 4 compatibility, JSON parsing safety, ADR review, and project philosophy
docs. The official AI SDK docs currently describe the SDK as a TypeScript
toolkit for building AI-powered applications and agents across React, Next.js,
Vue, Svelte, Node.js, and other runtimes.

## Source Scope

This entry is scoped to working in the official `vercel/ai` repository. It is
not a generic Vercel deployment agent, not a Next.js framework contributor
agent, not a v0 prototyping workflow, and not a general AI app generator. Use it
when the task is about investigating, patching, testing, reviewing, or
documenting the upstream AI SDK monorepo.

## Use Cases

- Give Claude a source-backed role for reading the Vercel AI SDK `AGENTS.md`
  before touching the monorepo.
- Investigate bugs in `packages/ai`, provider interface packages, provider
  implementations, UI integrations, docs, examples, or codemods.
- Build a focused validation plan that distinguishes package build, Node tests,
  Edge tests, full type checks, lint/format checks, examples, and docs work.
- Review provider API changes for compatibility with shared interfaces,
  utilities, docs, examples, and snapshots.
- Keep AI SDK changes aligned with current ADRs, project philosophy docs, Zod
  compatibility expectations, and JSON parsing safety rules.

## Duplicate Check

Checked current `upstream/main`, open PR titles, open PR changed files, issue
titles, source URLs, and existing content entries for `Vercel AI SDK`,
`vercel/ai`, `ai-sdk.dev`, `AI SDK`, `streamText`, and `generateText` before
drafting this entry. No existing `content/agents`, `content/skills`,
`content/hooks`, or `content/mcp` entry covers a source-backed Vercel AI SDK
repository contributor agent. Existing Next.js, Vercel MCP, v0, and Supabase
MCP entries are adjacent ecosystem coverage, not duplicate AI SDK monorepo
contributor guidance.

## Editorial Disclosure

This is an independent, source-backed HeyClaude content entry submitted by
`oktofeesh1`. It is not sponsored by Vercel or the Vercel AI SDK maintainers.
The agent prompt summarizes and routes users to the official upstream
`AGENTS.md`, documentation, and repository sources rather than repackaging the
AI SDK project.

Source citations

Add this badge to your README

Show that Vercel AI SDK Repository Contributor Agent for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/agents/vercel-ai-sdk-repository-contributor-agent.svg)](https://heyclau.de/entry/agents/vercel-ai-sdk-repository-contributor-agent)

How it compares

Vercel AI SDK Repository Contributor Agent for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field

Source-backed Claude agent prompt for contributing to the official Vercel AI SDK monorepo using its AGENTS.md guidance, pnpm workspace commands, package build and test boundaries, provider architecture, Zod compatibility rules, JSON parsing safety, ADR review, and documentation sources.

Open dossier

Source-backed Claude agent prompt for contributing to the official Astro monorepo using its AGENTS.md guidance, pnpm workspace commands, package-local testing, bgproc dev server management, agent-browser UI checks, and Astro docs sources.

Open dossier

Source-backed Claude agent prompt for contributing to the official prisma/prisma monorepo using its AGENTS.md guidance, pnpm workspace commands, package-filtered tests, database fixture expectations, Prisma 7 architecture notes, and contributor safety rules.

Open dossier

Source-backed Claude agent prompt for contributing to the official vercel/next.js monorepo using its AGENTS.md guidance, pnpm workspace commands, package-filtered builds, Turbopack and Rust boundaries, mode-specific tests, PR triage rules, and secrets-safety notes.

Open dossier
Next steps
Trust
Review statusReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceSource-backedSource-backedSource-backedSource-backed
Submitteroktofeesh1oktofeesh1oktofeesh1oktofeesh1
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
BrandVercel AI SDK
Categoryagentsagentsagentsagents
SourceSource-backedSource-backedSource-backedSource-backed
AuthorVercelAstroPrismaVercel
Added2026-06-042026-06-042026-06-042026-06-04
Platforms
Harness
Source repo
Safety notesThis agent is for contributing to the official Vercel AI SDK repository, not for generating generic AI applications or replacing the AI SDK documentation. The monorepo uses pnpm workspaces and Turborepo. Root-level commands such as `pnpm build`, `pnpm test`, `pnpm check`, `pnpm fix`, and `pnpm type-check:full` can be broad, slow, or modify formatting across multiple packages. `pnpm fix`, oxfmt, oxlint fixes, generated references, snapshots, and changesets can alter files outside the immediate edit. Inspect the diff before committing. Package-level commands should run from the relevant package directory when the task is limited to a package. Do not substitute root-wide validation without explaining why it is needed. The AI SDK supports both Zod 3 and Zod 4. Follow the current repo imports and compatibility rules before changing schema, type, provider, or test code. Do not use direct `JSON.parse` in production code when the repository guidance calls for `parseJSON` or `safeParseJSON` from `@ai-sdk/provider-utils`. Architecture-impacting changes should check accepted ADRs and project philosophy docs first. Stop and ask before contradicting an accepted decision. Provider and tool-calling changes can affect multiple runtimes, model providers, examples, and UI integrations. Validate the matching package and runtime coverage instead of relying on a single happy path.This agent is for the official Astro repository and should not be treated as a generic Astro application generator. The Astro monorepo has broad format, lint, build, and test commands. Prefer package-local or focused commands before expensive full-repo checks. `pnpm format` and code generators can modify many files. Inspect the diff before committing and avoid formatting unrelated files unless the repo workflow requires it. Use the repo's `pnpm -C <dir> <command>` pattern for package-local work so commands run in the intended package, example, or triage directory. Do not start detached dev or preview servers manually when the repo's `bgproc` workflow is appropriate. Clean up long-running servers after verification. Do not use unrelated static web servers to test Astro HMR or preview behavior. Use Astro's documented dev and preview paths. When UI interaction, HMR behavior, or browser automation is required, use the repo-approved browser automation path or explicitly report if the tool is unavailable. Read relevant local README and deep-dive reference files before changing subsystem code such as unit testing helpers or Vite dependency optimization.This agent is for contributing to the official Prisma repository, not for generating generic Prisma application code. Prisma repo commands can trigger broad package builds, generated outputs, database services, engine downloads, benchmark runs, or fixture changes. Start with focused validation before full-root commands. `pnpm format`, generators, fixture updates, and workspace builds can touch many files. Inspect the diff and avoid unrelated cleanup. Database-backed tests may require `.db.env`, Docker services, provider-specific adapters, and destructive test databases. Do not run them against production or shared databases. Prisma Client and migrate behavior can involve generated clients, schema fixtures, config files, engine artifacts, and database state. Treat generated and fixture changes as review-critical. Do not assume older Prisma architecture from memory. Prefer the current AGENTS.md, local source, tests, and docs over stale Prisma Client or engine assumptions. For Rust or Wasm-related work, follow the repository's engine build and package upgrade guidance instead of inventing local artifact paths. Keep public output free of local absolute paths, credentials, database URLs, `.db.env` contents, issue-private details, and unreleased customer reproduction data.This agent is for contributing to the official Next.js framework repository, not for generating generic Next.js applications. Next.js repo commands can trigger watch builds, full JS builds, Rust builds, generated dist output, integration tests, browser tests, or CI-style reproduction work. Prefer focused validation first. `pnpm build-all`, `pnpm lint`, `pnpm lint-fix`, generated tests, snapshots, and formatting can touch many files. Inspect the diff before committing. Mode-specific tests matter. Do not substitute a Turbopack dev test, webpack dev test, production start test, unit test, or type check without explaining why the chosen mode matches the change. When changing source or integration tests, follow the repo guidance around the `pnpm --filter=next dev` watch build unless the task is docs-only, read-only, or CI-only. Do not leave watch builds or dev servers running after verification. Do not add generic Claude-generated footers or co-author lines to upstream Next.js commits or PR text. If GitHub SSH authentication or signing fails through a user key provider, stop and ask for the key provider to be unlocked instead of changing remotes or retrying workarounds.
Privacy notesAI SDK repo work can expose local file paths, provider names, model IDs, API request shapes, streamed text, tool-call arguments, fixtures, snapshots, telemetry examples, error payloads, and test output. Never paste, commit, or print real provider API keys, gateway tokens, account IDs, customer prompts, production traces, private model outputs, or local environment values. Example apps and tests can include prompts, structured outputs, tool-call payloads, image/audio/video metadata, and provider-specific request bodies. Use synthetic fixtures when sharing publicly. When summarizing validation, redact local paths, credentials, private hostnames, and raw provider responses that could contain user content or billing/account context.Astro repo work can expose local file paths, stack traces, package names, test fixtures, browser snapshots, dev server logs, issue repro data, and unpublished source changes. Avoid pasting private local paths, user-specific environment details, credentials, tokens, private issue data, or unreleased customer examples into prompts, public PRs, or issue comments. Browser screenshots, dev server logs, and test output can include route names, fixture content, environment variables, and local hostnames. Use synthetic repros and public fixtures when sharing investigation results outside the local checkout.Prisma repository work can expose local database URLs, `.db.env` values, Docker service names, fixture data, generated client output, query logs, stack traces, benchmark output, and local file paths. Never paste real connection strings, tokens, customer schemas, private database contents, or internal reproduction data into prompts, commits, issues, or public PR comments. SQL commenter, query insight, trace, and raw query tests may include query shapes or metadata. Review logs before sharing them outside the local environment. Prefer synthetic schemas, public fixtures, and redacted validation summaries when reporting database behavior.Next.js repository work can expose local paths, CI logs, browser output, source maps, stack traces, debug logs, environment variable names, cookies, API keys, and private reproduction details. Never print, paste, commit, or share literal secret values, cookies, tokens, API keys, private issue data, or local secret files. Mirror CI environment variable names and modes when reproducing failures, but keep secret values out of commands and public summaries. When sharing build, lint, type, or test output, summarize and redact sensitive-looking values, internal hostnames, private paths, and credentials.
Prerequisites
  • A local checkout or source snapshot of the official `vercel/ai` repository.
  • Review the current official `AGENTS.md` before using this agent, because repo instructions, supported Node versions, and package commands can change.
  • Node.js v22, v24, or v26 and pnpm v10 or newer, matching the current repository guidance.
  • Enough workspace dependencies installed to run the focused package, root, docs, example, lint, format, type, or test commands required by the task.
  • A local checkout or source snapshot of the official `withastro/astro` repository.
  • Review the current official `AGENTS.md` before using this agent, because repo instructions can change.
  • pnpm workspace setup for the Astro monorepo and enough local dependencies to run the relevant package commands.
  • Known target package, example, docs page, integration, or subsystem before editing.
  • A local checkout or source snapshot of the official `prisma/prisma` repository.
  • Review the current official `AGENTS.md` before using this agent, because Prisma repository instructions can change.
  • Node and pnpm versions compatible with the repository's root `package.json`.
  • Enough dependency setup to run relevant pnpm workspace, Turborepo, package-filtered, Jest, Vitest, or benchmark commands.
  • A local checkout or source snapshot of the official `vercel/next.js` repository.
  • Review the current official `AGENTS.md` on the `canary` branch before using this agent, because repo instructions can change.
  • pnpm workspace setup for the Next.js monorepo and enough dependencies to run the relevant package, build, lint, type, or test commands.
  • Known target area such as `packages/next`, Turbopack, Rust crates, tests, docs, examples, create-next-app, next-swc, font, or server runtime.
Install
Config
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Related guides

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.