Methodology Reviewer — Development agent for Claude Code
Single-agent meta-review of the agentic-ontology methodology.
How to install Methodology Reviewer
Installs to ~/.claude/agents/opendatadiscovery-odd-team-methodology-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/opendatadiscovery/odd-team/HEAD/.claude/agents/methodology-reviewer.md -o ~/.claude/agents/opendatadiscovery-odd-team-methodology-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Methodology Reviewer does
name: methodology-reviewer description: Single-agent meta-review of the agentic-ontology methodology. Traces the WHOLE current methodology end-to-end — APPROACH.md (every section + every revision), the ADRs, the agent contracts, the skills, the playbooks, the case-law, and the live artefacts — diffs against the prior review, runs fresh blind spot-checks against the real target source, and emits real gaps + real improvement proposals (including subtraction). One cheap pass; replaces the six-e
Alternatives in Development
- Agentica Agent — You are a specialized agent for building Python agents using the Agentica SDK 3.6k ★
- RAG Specialist — GAIA RAG and agentic-retrieval specialist 1.5k ★
- Workflow Plan Checker — Validates plan quality with up to 3 revision rounds 530 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Feature Advisor
Query-time advisor subagent. Reads the maintainer's free-form question ("I want to add X — what's affected?"),
Learner Diagnostic
Assesses learning approach across 5 dimensions from Justin Sung's methodology. Use when user wants to evaluate
Ade CLI
Coding agents asked to read contracts, claims, or financial PDFs hallucinate structure unless the extraction t
ADR Reviewer
Strict Architecture Decision Record reviewer. Reviews ADRs for section completeness, context-decision alignmen
Layout Specialist
Grid, spacing, density, and responsive breakpoint specialist. Given a persona and product description, produce
Tp Debugger
PROACTIVELY use this when the user reports a bug, stack trace, error message, failing behaviour, or asks "why
Related Skills
Iterate Revision
Revise one manuscript section against the reviewer team until DONE/BLOCKED/HALT. Writer ↔ reviewer loop driven
Experiment Formalisation
Formalise an experiment as a machine-checkable record layer — EXPO/SUMO/PROV-O with verified vocabulary only,
Ontology Skills
A domain-agnostic methodology for building, extending, reviewing, and refactoring ontologies, domain models, t