Goal Forge — Development skill for Claude Code
Portable self-goal + independent-adversary methodology for Claude Code agents.
How to install Goal Forge
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open vzert/goal-forge and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Goal Forge does
Portable self-goal + independent-adversary methodology for Claude Code agents. Hardens the built-in /goal.
Alternatives in Development
- Kaizen — Applies continuous improvement methodology with multiple analytical approaches, based on Japanese Kaizen philo 663 ★
- Fusion Opus4.8 — Fusion panel of two independent Opus 4.8 runs, judged by Opus 4.8 (opus4.8-4.8) 468 ★
- Claude Code Research — Independent research on Claude Code internals, Claude Agent SDK, and related tooling 148 ★
README
goal-forge
A Claude Code plugin marketplace for one plugin: **goalspec** — a portable *self-goal + independent-adversary* methodology that turns a terse request into a grounded, falsifiable goal-spec, verifies the outcome with an independent adversary, and closes through a fail-open completion gate.
It is a junior→senior uplift for agents, packaged so anyone can install it in one command and run it on any domain with **zero configuration** —
Related Skills
Teamwork Dsh
Portable multi-agent orchestration runtime with DeepSeek Harness plugins, independent review and acceptance ga
Anti Subagent
FUCK SUBAGENTS. Multi-agent architecture built with autonomous full agents instead of native subagents. Superv
Ccledger
Team usage ledger for Claude Code. Self-hosted OTLP ingest into SQLite, with a per-person dashboard. Independe
Desk Complete
Bring one underlying to a complete artifact set against checkable criteria. Built for goal-based loops.
Waypoint Videolink App
A single static page built to open (and close) a screen-recorded demo of Waypoint — a browser-based agent that
Mem Forge
Self-evolving, evidence-based memory layer for coding agents and development teams.
Related Agents
Test Quality Adversary
Fresh-context, refute-framed review of what the TESTS actually promise — the head-of-QA loss function. Hunts s
Studio Director
Phase-aware Forge AI Studio orchestrator. Splits one approved phase goal into independent workstreams, delegat
Vbw QA
Verification agent using goal-backward methodology to validate completed work. Read-only (permissionMode plan)