Foundry Voss — Development agent for Claude Code
Use this agent for agent quality calibration, SKILL.md creation and refinement, agent output evaluation, crew performance measurement, and Foundry operations (Forge, Temper, Calibrate).
How to install Foundry Voss
Installs to ~/.claude/agents/sector137-crew-foundry-voss.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/sector137/crew/HEAD/agents/foundry-voss.md -o ~/.claude/agents/sector137-crew-foundry-voss.md Restart Claude Code, or start a new session, for it to be picked up.
What Foundry Voss does
name: foundry-voss description: "Use this agent for agent quality calibration, SKILL.md creation and refinement, agent output evaluation, crew performance measurement, and Foundry operations (Forge, Temper, Calibrate). Owns the Foundry — the only component that operates on the crew itself." model: sonnet color: red
Voss Praxis — Agent Architect / Foundry Owner
You are **Voss Praxis**, the Agent Architect and owner of The Foundry on Sal's crew. You build, evaluate, and calibrate agen
Alternatives in Development
- Svelte Recurrence Sweep — Given a defect just found or fixed in a SvelteKit app (apps/moderator, apps/auth, apps/creator-studio), finds 7.2k ★
- Review Bugs — Reviews code changes for potential bugs found by single-threaded sequential reasoning: logic errors, null safe 432 ★
- Librarian Critic — Literature quality critic 250 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Doey Critic
Quality critic — fast, ruthless, minimal. Reviews code and output for correctness, clarity, and necessity. Own
Loop Refiner
Apply critique issues to produce a minimally changed improved artifact. Use proactively within /aif-loop when
Review Fixer
Applies what CodeRabbit and Sourcery found on a pull request. Use after fetch_review has written .claude/forge
Forge
Claude Code driver agent for Forge Core. Tracks coverage/speed/quality, rotates strategies on stagnation, and
Fk Benchmarker
Owns the measurement protocol - noise floor, warm-up, clock ramp, repeats, CUDA sync, peak VRAM, launch counts
Artifact Critic
Checks strategy artifacts (TL;DR cards, output documents) for structural conformance, voice conformance, and r
Related Skills
Calibrate
Run the calibration pipeline for a single fixture, all active fixtures, or resume a failed run.
Calibrate Voice
Run an empirical calibration round: regenerate the 8-brief matrix, measure, collect owner ratings, codify ever
Empirica
Make AI agents and AI workflows measurably reliable. Epistemic measurement, Noetic RAG, Sentinel gating, and g