forge-core
01Plugin Claude Code
Module-building skills for the forge ecosystem.
Plugin Claude Code
Module-building skills for the forge ecosystem.
Instructions file CodexOpenCode
AGENTS.md instructions for N4M3Z/forge-core, covering agents.md -- forge-core, build / install / verify, project structure, skills and skill file convention.
Instructions file
Claude Code instructions for N4M3Z/forge-core, covering claude.md, skills, build & test, architecture and skill companion pattern.
Instructions file Gemini CLI
Gemini CLI instructions for N4M3Z/forge-core, covering gemini.md, project overview, core technologies, building and running and key commands.
Agent
Data analyst — success metrics, KPIs, measurement strategies, business impact analysis, data-driven evaluation. USE WHEN metrics design, success criteria, impact analysis, data strategy.
Agent
Documentation specialist — README quality, API docs, developer experience, onboarding clarity. USE WHEN documentation review, README evaluation, developer experience assessment, onboarding analysis.
Agent
Forensic security analyst — PII detection, secret scanning, identity leak auditing across git history, staged changes, working tree, all branches, and cross-repo GitHub-wide audits. USE WHEN PII scan, leaked name, pre-publication audit, git history audit, secret scan, security review, forensic analysis, scan my github.
Agent
Product manager — requirements clarity, user goals, roadmap alignment, market fit, prioritization trade-offs. USE WHEN requirements review, feature scoping, roadmap decisions, product strategy.
Agent
Provenance and deployment integrity auditor -- validates SLSA sidecars, manifests, and drift across providers. USE WHEN check provenance, audit deployment, verify integrity, detect drift, stale files, manifest check.
Agent
Security policy architect — threat modeling, security posture, policy design, architectural risk. USE WHEN security review, threat model, security policy, architectural security assessment.
Agent
Skill quality reviewer — evaluates SKILL.md frontmatter, description trigger effectiveness, body content quality, and progressive disclosure. USE WHEN reviewing a newly created or modified skill, checking skill quality, evaluating trigger phrases, auditing skills before deployment, improving skill description.
Agent
System architect — design patterns, boundaries, dependencies, scalability, long-term trade-offs. USE WHEN architecture decisions, system design, boundary analysis, scalability assessment.
Agent
Devil's advocate — stress-tests ideas, plans, proposals, and decisions. USE WHEN critical analysis, challenge assumptions, decision review, risk assessment.
Agent
Strategic web researcher — multi-query decomposition, parallel search, scholarly synthesis with citations. USE WHEN deep research, topic investigation, source analysis, evidence synthesis.
Hook
Runs before the context is compacted, executing preserve-adrs.sh via bash. From N4M3Z/forge-core.
Hook
Runs before the agent uses a tool for Write, Edit and Bash tool calls, executing gate-frontmatter.sh, guard-naming.sh, adr-context.sh and safety-net.sh via bash (5 commands). From N4M3Z/forge-core.
Skill Claude CodeCodex
Adopt a community skill from an upstream URL into forge. Fetches the source, applies transforms, produces a working SKILL.md with SLSA provenance. USE WHEN adopting a community skill from aitmpl, anthropics/skills, or a similar catalog.
Skill Claude CodeCodex
Find, read, create, validate, and capture Architecture Decision Records. USE WHEN ADR lookup, architecture decision, project context, decision history, create ADR, new ADR, validate ADR, capture ADRs, decisions directory, or editing any ADR file.
Skill Claude CodeCodex
Collaborative ideation before implementation — explore context, clarify intent, propose approaches. USE WHEN starting creative work, new features, design decisions, or modifying behavior.
Skill Claude CodeCodex
Create, validate, or audit agent definitions. USE WHEN create agent, new agent, build agent, scaffold agent, validate agent, audit agents, agent conventions, agent frontmatter.
Skill Claude CodeCodex
@GeminiAgent.md.
Skill Claude CodeCodex
Create and validate module hooks. USE WHEN create hook, new hook, write hook, scaffold hook, validate hook, check hook, hook conventions, hook events, hook structure.
Skill Claude CodeCodex
Design, build, and validate forge modules. USE WHEN create module, new module, scaffold module, validate module, check module, audit module, module structure, module conventions, module architecture.
Skill Claude CodeCodex
Create, validate, and publish Claude Code plugins from forge modules. USE WHEN create plugin, validate plugin, publish plugin, marketplace, plugin.json, cowork plugin.