Evanflow Overseer — Development agent for Claude Code
Read-only review subagent for one coder's output (or for cross-coder integration review) in the evanflow-coder-overseer pattern.
How to install Evanflow Overseer
Installs to ~/.claude/agents/evanklem-evanflow-evanflow-overseer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/evanklem/evanflow/HEAD/agents/evanflow-overseer.md -o ~/.claude/agents/evanklem-evanflow-evanflow-overseer.md Restart Claude Code, or start a new session, for it to be picked up.
What Evanflow Overseer does
name: evanflow-overseer description: Read-only review subagent for one coder's output (or for cross-coder integration review) in the evanflow-coder-overseer pattern. Reports findings; never fixes. Tool-restricted to prevent any modifications — Read/Grep/Glob only, no Edit/Write/Bash. The role separation is the QA signal. tools: Read, Grep, Glob model: sonnet
You are an EvanFlow Overseer. You review one coder's work (or, for the integration overseer, the combined work of all coders) in t
Alternatives in Development
- Workflow Integration Checker — Cross-phase integration validation for milestone audits 530 ★
- Verify Completeness — A verification agent that ensures all artifacts (raw outputs, manuscript tables, manuscript figures) are prope 134 ★
- Contract Tester — Validate service interactions and prevent integration drift 108 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Evanflow Coder
Implementation subagent for one decomposed unit of work in the evanflow-coder-overseer pattern. Uses vertical-
Bug Reproduction Validator
Validates bug reports by attempting to reproduce the reported behavior before fixes begin. Use when receiving
Rfe Scorer
Scores a single RFE issue against quality rubric. Restricted to Read and Write only to prevent prompt injectio
E2e Finding Verifier
Use after e2e-reviewer or scan.sh reports findings, to adversarially verify ONE finding in its real code conte
Fix Planner
Read audits in .claude/audits/. Deduplicate and prioritize findings. Output to .claude/audits/FIXES.md.
Hatch3r Fixer
Targeted fix agent that takes structured reviewer output and implements fixes for Critical and Warning finding
Related Skills
Security Watch
One security-watch pass over an EVM / Solidity repo — deps + static analysis + risky-pattern grep + recent adv
Review UX Audit
Full UX audit of a frontend codebase. Produces persona cards, journey maps, heuristic sweep, anti-pattern find
App Review
Review code and present prioritized findings — read-only, never auto-fixes