By vivecuervo7
Browser-automation agent team for Claude Code — drive tasks end-to-end against an ephemeral chromium session, accrete reusable snippets, teach forge new flows turn-by-turn, compose verified Playwright specs, and re-run specs on demand for paired before/after evidence. Project-specific conventions (accounts, env handling, setup) are documented in forge/hints/ rather than baked into forge.
Drive a multi-step browser task end-to-end against an ephemeral chromium session managed by playwright-cli. Teammate role in the forge agent team — drives the browser, narrates meaningful steps to the snippet-author teammate via SendMessage, can be asked clarifying questions by snippet-author / spec-writer / spec-verifier teammates. Goes idle after the drive completes; stays available for follow-up questions until the team disbands.
Write snippets from a driver's live browser work. Teammate role in the forge agent team — receives SendMessage updates from the driver as the drive progresses, decides which steps are snippet-worthy with full hindsight, writes snippets to the project's forge/snippets/. Can SendMessage the driver clarifying questions (selector choices, env handling, recovery decisions).
Run the spec the spec-writer just produced and report whether it passes from a cold start. Teammate role in the forge agent team — receives the spec path from spec-writer when it's ready, invokes forge-run-spec.mjs, captures pass/fail. On failure, surfaces the error to driver and spec-writer for clarification; iterates with their answers until the spec passes or escalates to the lead.
Write a self-contained Playwright .spec.ts that reproduces the driver's task. Teammate role in the forge agent team — receives the driver's final-state summary at the end of the drive, composes the spec around existing snippets where the driver invoked them and inlines fresh code for the rest, adds assertions on captured values. Can SendMessage the driver clarifying questions (selectors, captured values, recovery decisions).
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A browser-automation team for Claude Code. Forge spawns a small mesh of agents that drive a real browser, capture reusable snippets, and (on request) compose verified Playwright specs from the work.
The default mode just does the thing you asked for. Spec mode is opt-in for when a flow is worth pinning into CI. If the team gets genuinely stuck, it escalates back to you with what it tried and what blocked it rather than spinning.
brew install playwright-cli. Forge wraps it.Supported on macOS, Linux, and Windows.
Install the plugin (one time per machine):
claude plugin marketplace add vivecuervo7/forge
claude plugin install forge@vivecuervo7
Enable experimental agent teams in ~/.claude/settings.json, then restart Claude Code:
{ "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" } }
Scaffold your project from inside it:
/forge init
This creates forge/ with a hints/ directory, a fallback Playwright config, and a self-documenting .gitignore.
Drive a task. For an unauthenticated site, the bare scaffold is enough:
/forge <describe what you want done>
That launches a fresh chromium and goes. For sites with auth or other project-specific behaviour, author hint files in forge/hints/ (see forge/hints/README.md for guidance). All five hints are optional and additive: write only what you need.
Want to see forge run end-to-end before adopting it? Try the samples — three project-shaped directories with hints already authored and prompt-by-prompt walkthroughs against public test sites. 5–15 minutes per walkthrough.
| Command | What it does |
|---|---|
/forge init | Scaffolds the forge/ directory convention into the current project. Idempotent — the starting point for any new project. |
/forge <task> | Drive mode. Driver + snippet-author. Does the task end-to-end, accretes reusable snippets from novel work. The everyday command. |
/forge spec <task> | Spec mode. Adds spec-writer + spec-verifier. Composes a self-contained .spec.ts and confirms it passes from a cold start. Also fires on natural-language signals — "create a spec for AE-1775", "write a spec that…", "capture as a spec". |
| Command | What it does |
|---|---|
/forge teach <topic> | User pilots forge turn-by-turn, signals snippet boundaries explicitly, and weaves project-specific gotchas (fallbacks, retries, conditional branches) into snippet bodies. The deliberate library-building channel — useful when the app has quirks the agent can't be expected to discover. Also fires on "teach forge how to …" / "let me show forge how to …" phrasings. |
| Command | What it does |
|---|---|
/forge run <spec|last|latest> | Re-runs a verified spec via the standalone runner. No team spawned. |
/forge export <spec-name> | Exports a composed spec to a self-contained inlined form, suitable for shipping into another test suite. |
Add record as <label> to a run invocation to capture a video at forge/videos/<spec>-<label>.webm. /forge run last spec, record as before → fix the bug → /forge run last spec, record as after produces paired evidence for a PR.
Try a sample before adopting forge for your own project. Each sample is a project-shaped directory — committed hints, scaffolded config, real-forge-output seed snippets — plus a prompt-by-prompt walkthrough you run yourself.
| Sample | What you'll see |
|---|---|
samples/shop/ | Authentication, multi-account hint pattern, full spec-mode pipeline with verifier iteration, and two browsers running in parallel under different accounts |
samples/internet/ | Variant-arg parameterisation — one snippet covers a family of probe pages |
samples/widgets/ | Compositional decomposition — fill + read snippets compose into larger flows |
Start with shop if your work involves any authenticated app — that walkthrough exercises the most surface area. Each sample's README has the exact commands; budget 5–15 minutes per walkthrough.
.spec.ts. Forge accretes snippets across drives and bakes project knowledge into reusable hints.npx claudepluginhub vivecuervo7/forge --plugin forgeA developer journaling system for Claude Code — log work, recap progress, search history, attach media
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.