Brief Author Medium — Development agent for Claude Code
A/B control arm — identical to brief-author but at medium effort.
How to install Brief Author Medium
Installs to ~/.claude/agents/vinipy12-lateralus-workflow-brief-author-medium.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/vinipy12/lateralus-workflow/HEAD/agents/brief-author-medium.md -o ~/.claude/agents/vinipy12-lateralus-workflow-brief-author-medium.md Restart Claude Code, or start a new session, for it to be picked up.
What Brief Author Medium does
name: brief-author-medium description: A/B control arm — identical to brief-author but at medium effort. Used only to measure whether effort changes brief completeness. tools: Read, Grep, Glob, Bash, WebFetch, Write effort: medium
You write lane briefs. That is the whole job. You do not implement, and you do not dispatch — you produce one file the orchestrator hands to a Codex lane.
This runs at high effort deliberately. Brief quality is the dominant failure mode in this harness: every
Alternatives in Development
- Playcanvas Editor Reviewer — Reviews code changes related to PlayCanvas Editor integration, scripting, assets, scenes, version control, and 22 ★
- Verify Documentation — STAGE 4 - Documentation and API contract validation 21 ★
- Size Check — Build the vlist library and measure gzipped bundle sizes per feature 16 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
GPT Astra Med
External worker: gpt-6-astra at medium effort, running in the codex CLI. Give it a self-contained brief with g
GPT Sol Med
External worker: gpt-6.1-sol at medium effort, running in the codex CLI. Give it a self-contained brief with g
Capcut Caption Burn
Captions one talking-head video with a transparent ProRes 4444 overlay pixel-identical to CapCut's auto-captio
S55 Verifier
Sonnet 5.5 verifier on medium, the default verifier. Use after every builder pass: checks the brief's acceptan
Exec Standard
MID tier at medium effort. Execution agent for well-bounded implementation in an isolated git worktree - new s
Medium
Implementer for standard feature work (Sonnet, high effort). Use for a well-specified ticket or vertical slice
Related Skills
Plan Check
You are now a task list completeness checker. Run hard-gate checks against the input tasks.json and output whe
Ralph Run Diagnostics
Evaluates whether the RALPH loop followed policy: correct task selection, verification level selection, requir
Build Icp
Build 13-section ICP Document with Completeness Score = 80. Consumes Market Research Brief, produces ICP Docum