Occam — Development agent for Claude Code
Review agent implementing Hunter's review-gate method.
How to install Occam
Installs to ~/.claude/agents/railly-skills-occam.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Railly/skills/HEAD/subagents/occam.md -o ~/.claude/agents/railly-skills-occam.md Restart Claude Code, or start a new session, for it to be picked up.
What Occam does
name: occam description: Review agent implementing Hunter's review-gate method. Runs deterministic checks first, then focused lenses, then adversarial verification of every finding at the layer of the claim. Use for pre-push review of a diff, PR review, and post-implementation checks. Runs on a different model than kepler (the writer) by design. Experimental (foundry maturity), replaces sage/local-reviewer for new work. tools: Read, Grep, Glob, Bash model: opus
You are occam, Hunter's r
Alternatives in Development
- Get Commit ID — gh api repos/OWNER/REPO/pulls/PR_NUMBER --jq '.head.sha' gh api repos/OWNER/REPO/pulls/PR_NUMBER/comments \ 1.3k ★
- Dashclaw Drift Auditor — Audits DashClaw's drift-prone hardcoded counts and version stamps — SDK method counts (Node/Python), MCP tool/ 297 ★
- .github/workflows/redteam.yml — name: Continuous Red Team Assessment on: push: branches: [main, develop] pull_request: branches: [main] schedu 213 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Refute Verifier
Clean-context skeptic that tries to REFUTE each draft finding or claim it is given — verdicts CONFIRMED / REFU
Stamity Reviewer
Reviews a change set across ten quality lenses and returns a verdict with confidence and graded findings, each
Kepler
Evidence-first implementation agent (Hunter's method). Executes a scoped change with an evidence chain, source
Assess Layer Scorer
Scores a codebase against the /assess 0-8 layered contract model, reading the deterministic run-context.json a
Wiki Sync
Use this agent when syncing the vault git repository during automated maintenance cycles. Typical triggers inc
Sp Reviewer
Use as a pre-push guardrail before committing or pushing. Runs lint, build, tests and a secret scan, reviews t
Related Skills
Push Back
Verify a claim against code+docs+memory before acting. Run when a finding/audit/recommendation looks suspect,
Adversarial Audit Engine
Cross-model audit engine for documents and technical artifacts: hallucination gate on verbatim quotes, claim v
Pre Deploy 3gate
Use right before a production deploy or when you're about to claim work is "shipped". Runs the 3-gate verifica