claude-forge
25Settings file Claude Code
Agent settings declaring 3 hook events (PreCompact, SessionStart, PostToolUse).
Settings file Claude Code
Agent settings declaring 3 hook events (PreCompact, SessionStart, PostToolUse).
Skill Claude CodeCodex
Structured completion-report contract for every dispatched Boss, validated by forge-report.cjs. Use when dispatching a subagent or ingesting its final report — completion contract, validation.
Skill Claude CodeCodex
Forge playbook for AI agents, LLM apps, and eval harnesses. Use for agent, LLM app, tool-calling, function calling, MCP tool, prompt injection, eval, benchmark, guardrail, fallback.
Skill Claude CodeCodex
Forge playbook for contract-first APIs. Use for API, REST, GraphQL, gRPC, OpenAPI, endpoint, auth, JWT, versioning, rate limit, idempotency, contract test, backend.
Skill Claude CodeCodex
Forge playbook for chat bots — Discord, Slack, Telegram. Use for bot, slash command, webhook, signature verification, OAuth scopes, rate limit, dead-letter, interaction handler.
Skill Claude CodeCodex
Forge structured-ideation playbook. Use BEFORE building when the approach isn't obvious — brainstorm, options, trade-offs, alternatives, design direction, which way to build.
Skill Claude CodeCodex
Forge playbook for CLIs and dev tools. Use for CLI, command line, argparse, flag, --help, exit code, stdin, stdout, pipe, dry-run, cross-platform, terminal, subcommand.
Skill Claude CodeCodex
Forge playbook for CMS work — WordPress and headless CMS. Use for CMS, WordPress, theme, plugin, custom post type, WP-CLI, Contentful, Sanity, Strapi, Payload, content model.
Skill Claude CodeCodex
Forge code-review method — order, severity levels, Codex handoff. Use before any commit or when asked to review code — code review, check my code, PR review, before I commit.
Skill Claude CodeCodex
Forge playbook for data engineering — ETL/ELT, dbt/SQL pipelines. Use for data pipeline, warehouse, Snowflake, BigQuery, dbt, incremental load, schema contract, data quality, PII.
Skill Claude CodeCodex
Forge systematic-debugging playbook. Use for ANY bug, crash, stack trace, failing test, or regression — debug, root cause, bisect, flaky test — before proposing a fix.
Skill Claude CodeCodex
Read-only full-codebase priming scanner. Use before a PRD or big refactor, or onboarding into an unfamiliar project — deep learn, prime the codebase, scan the project, risk list.
Skill Claude CodeCodex
Detects drift between cited external docs (Claude Code, n8n nodes) and what our skills claim. Use before major n8n work or on /forge docs-check — doc drift, source verification, staleness.
Skill Claude CodeCodex
Runs Forge's self-test + secret-leak scan across source, tests, and dashboard. Use before shipping or when asked to test everything, check it executes, or find leaks.
Skill Claude CodeCodex
Forge playbook for e-commerce and cashflow shops. Use for shop, store, cart, checkout, product, inventory, Shopify, WooCommerce, Etsy, Stripe, order fulfillment, oversell.
Skill Claude CodeCodex
Forge playbook for Electron desktop apps. Use for electron, desktop app, .exe, installer, IPC, contextBridge, contextIsolation, nodeIntegration, code signing, auto-update.
Skill Claude CodeCodex
Forge playbook for browser extensions (Chrome/Edge MV3). Use for chrome extension, manifest v3, service worker, content script, permissions, CSP, Web Store, store policy.
Skill Claude CodeCodex
Forge playbook for design-to-code. Use for figma, design to code, mockup, design tokens, pixel-perfect, responsive, breakpoints, style guide, dev mode, handoff, accessibility.
Skill Claude CodeCodex
Forge playbook for full-stack apps — frontend + backend + database + auth. Use for full-stack, SaaS, CRUD app, Postgres, Supabase, JWT, session, signup, dashboard.
Skill Claude CodeCodex
Forge playbook for games — Canvas/WebGL/Phaser/Godot. Use for game, browser game, gameplay, game loop, win/lose state, soft-lock, frame rate, collision, save load, playtest.
Skill Claude CodeCodex
Advisory graded quality scoring for RAG/research/scraping/prediction output. Use alongside forge-verify for subjective answer quality — rubric, per-criterion score, source grounding.
Skill Claude CodeCodex
Scaffold design doctrine for an owner-gated production self-healing guardian (not live). Use only when designing auto-rollback, incident response, canary, circuit breaker automation.
Skill Claude CodeCodex
Detects a dispatched agent gone silent mid-run from events.jsonl. Use during multi-agent runs or when a run feels quiet — silent agent, stalled run, heartbeat check, timeout.
Skill Claude CodeCodex
Prompt Master intake — captures the real goal via one clarifying-question list before building. Use at the START of any /forge build/create/automate task — intake, requirements, scope, PRD.