Devflow Standards — Development agent for Claude Code
devflow reviewer for the Standards axis.
How to install Devflow Standards
Installs to ~/.claude/agents/jholhewres-devflow-devflow-standards.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/jholhewres/devflow/HEAD/agents/devflow-standards.md -o ~/.claude/agents/jholhewres-devflow-devflow-standards.md Restart Claude Code, or start a new session, for it to be picked up.
What Devflow Standards does
name: devflow-standards description: devflow reviewer for the Standards axis. Reviews one work item's change against the repo's written rules, then a baseline of code smells, from the review packet devflow assembles, and answers with one findings JSON object. tools: Read, Grep, Glob, Bash
Devflow reviewer: Standards
You review one change on one axis, **standards**: does it follow how this repo says code is written here? You work from the review packet named in your prompt: BASE, HEAD
Alternatives in Development
- Code Writer — Implements exactly one work packet — minimal diff, targeted checks, own-paths-only commits 16.1k ★
- Topic Specialist — Embodies a domain specialist by loading specified skills, then researches how something works using verified p 64 ★
- Scope Controls — Controls orchestrator — dispatches six subagents in two waves (org-wide issues, detections, dashboard ideas, p 54 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Reviewer Standards
Reviews a feature branch against the repository's written rules and returns typed, cited findings — rule viola
Review Axis
One axis of a code review, dispatched by the review-changes skill. Reads a diff against a single question — co
Bd Intake Extract
Extracts text, numbers and labels from source material and indexes the files. Returns EXIF, resolution and sha
Finding Judge
nightshift's Tier 2 for the reviewer. Decides what happens to each review finding (fix, drop, hold, out of sco
Migration Gate Runner
Use when the build and the tests have to be run in a given directory and the raw result reported without inter
Sensei
Genesis coordinator - the user talks to Sensei; it verifies requirements, plans, delegates authoring to Method
Related Skills
Mangchi
Iterative cross-model code refinement - Claude edits, Codex reviews one axis at a time with verification loop,
Educational Assessment AI Agent Platform
AI agent platform for K-12 assessment: standards-aligned item authoring with RAG and self-review, rubric-based
Habitusx
The AI Code Outcomes Index. What happens to AI-written code after it lands: revert rate, PR acceptance and sur