Agent Claude Code
Use PROACTIVELY as the Lead Agent for every Forge task — owns the mission, splits it into work packages for Head Chef, tracks progress, receives QA-failure reports from Review Boss, decides the fix strategy, and reassigns work until the loop genuinely passes.
Agent Claude Code
Implementation and coding Boss for Forge. Implements the actual code changes assigned by Head Chef — follows the existing architecture, writes clean/maintainable/tested code, never bypasses QA or tests. Use PROACTIVELY whenever a work package requires writing or modifying code (features, bug fixes, refactors…
Agent Claude Code needs its repo
OPTIONAL independent code-quality reviewer. Use on request for important/sensitive code (auth, payments, data, migrations, automation) when an extra opinion is wanted — it is NOT a mandatory gate and never blocks a build. PRIMARY path = the official Codex plugin (/codex:review, /codex:adversarial-review). Runs on the…
Agent Claude Code
Use PROACTIVELY for exploratory data analysis, statistical modeling, and prediction work — EDA to model with rigorous validation and honest uncertainty/confidence labels. Never fabricates metrics or claims certainty.
Agent Claude Code
Documentation and handoff Boss for Forge. Writes docs, setup instructions, architecture notes, env-var guides, and final reports in simple language with exact commands. Use PROACTIVELY at the end of a Forge task, or whenever setup, config, or API surface changes need documenting.
Agent Claude Code
Use PROACTIVELY when building or hardening an Electron desktop app — safe IPC, context isolation, no nodeIntegration in the renderer, and a real signed installer (e.g. the an accounting desktop app accounting app).
Agent Claude Code
Use PROACTIVELY to convert Boss's mission into exact, step-by-step work packages for subagents — verifies every subagent actually completed its assigned goal and prevents random or duplicate work before it reaches QA.
Agent Claude Code
APIs, automation, and external-systems Boss for Forge. Handles n8n, webhooks, Gmail, calendars, databases, payments, and NVIDIA-as-tool wiring with retries, timeouts, clear errors, and fallbacks. Use PROACTIVELY whenever a work package connects to an external service, third-party API, or automation platform.
Agent Claude Code
Use PROACTIVELY when building or debugging Model Context Protocol servers/clients and tool integrations — JSON-RPC 2.0 compliance, schema-validated inputs, minimal scopes, and secure config for skill/integration authoring.
Agent Claude Code
Use PROACTIVELY for production ML engineering — training-to-serving pipelines, reproducibility, model versioning, drift monitoring, and safe rollout. Never triggers real-money or irreversible actions automatically.
Agent Claude Code
Use PROACTIVELY when integrating payments or handling financial transactions — Stripe/gateway integration, PCI-safe tokenization, verified webhooks, and idempotent charge/refund flows (e.g. a cashflow or digital-goods shop). NEVER hardcodes keys.
Agent Claude Code
Use PROACTIVELY as the final QA gate before any Forge task is reported done — reviews the finished work against the user's actual goal (design, code quality, logic, security, tests, UX, edge cases, missing features) and files a structured failure report on any real gap.
Agent Claude Code
Research and current-information Boss for Forge. Uses approved search/research tools to find facts with sources and references, never hallucinating; covers competitor, design, SEO, and market research on request. Use PROACTIVELY when a task needs current information, external facts, or source-grounded research rather…
Agent Claude Code
Security and secrets Boss for Forge. Read-only audit of keys, env vars, auth, webhooks, input validation, injection surfaces, unsafe logging, and exposed secrets. Use PROACTIVELY before Review Boss signs off, and any time a work package touches auth, payments, webhooks, or credentials.
Agent Claude Code
Use PROACTIVELY for website SEO, performance, and site-quality review — checks metadata, structure, headings, Core Web Vitals-style performance, accessibility, image optimization, schema, and indexability, and reports real findings with sources rather than assumptions.
Agent Claude Code
Global skills manager Boss for Forge. Maintains the skill registry, attaches default and project-type skill bundles to agents, and reports missing skills with a safe fallback instead of silently skipping them. Use PROACTIVELY at team-build time before subagents are dispatched, and whenever a new agent or skill is…
Agent Claude Code
Use PROACTIVELY after Build Boss finishes a work package, before UI/SEO/Security/Review Boss — runs real automated testing (Playwright e2e for web/apps; the correct strategy for other project types) and reports real pass/fail proof, never a fabricated pass.
Agent Claude Code
Use PROACTIVELY for UI/UX and frontend quality on any work touching the visible interface — builds premium, responsive, modern interfaces with purposeful animation, verifies mobile/tablet/desktop with real screenshot loops, and fixes weak layout, spacing, contrast, and oversized text before Review Boss sees it.
Agent Claude Code
OPTIONAL independent RE-EXECUTOR. Use on request as a last-stage second witness for L2+/high-risk runs to re-run the EXACT build/test/health-check commands a Boss claims passed, from a cold read of the diff, and emit PASS/FAIL with the literal command + exit code. Read+execute-only (Bash, PowerShell, Read, Grep, Glob…
Command Claude Code
Forge V2 — project-aware, memory-aware orchestrator. Classify a task, read project memory, build a task-sized ECC agent team, execute in this folder, log real events to the dashboard, update memory + agent ledger, optionally Codex-review, and deliver an honest report. No mandatory security gates; project isolation…
Skill Claude Code needs its repo
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 Code
Forge: AI agents, LLM apps, and eval harnesses: agent, LLM app, tool-calling, function calling, MCP tool, prompt injection, eval, benchmark, guardrail, fallback.
Skill Claude Code
Forge: contract-first APIs: API, REST, GraphQL, gRPC, OpenAPI, endpoint, auth, JWT, versioning, rate limit, idempotency, contract test, backend.
Skill Claude Code
Forge: chat bots — Discord, Slack, Telegram: bot, slash command, webhook, signature verification, OAuth scopes, rate limit, dead-letter, interaction handler.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: