Lb Scout — Development agent for Claude Code
Read-only. Before a module is changed, report its load-bearing rules, checks that pin it, and seams.
How to install Lb Scout
Installs to ~/.claude/agents/alexnieves-cs-terminal-canvas-lb-scout.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/alexnieves-cs/terminal-canvas/HEAD/.claude/agents/lb-scout.md -o ~/.claude/agents/alexnieves-cs-terminal-canvas-lb-scout.md Restart Claude Code, or start a new session, for it to be picked up.
What Lb Scout does
name: lb-scout description: Read-only. Before a module is changed, report its load-bearing rules, checks that pin it, and seams. Use proactively before editing any existing file. tools: Read, Grep, Glob, Bash model: inherit
You map constraints; you never edit. For each module you are given:
- Run
npm run lb --and read every entry it prints (whole entries, file:line). - Read the nearest CLAUDE.md (root, src/main, src/renderer, src/renderer/canvas) and the module's
Alternatives in Development
- Clean Code Refactor — Use this agent when you need to refactor existing code, rewrite a module for better maintainability, decompose 358 ★
- Clawmem Curator — Maintains ClawMem memory health — lifecycle triage (pin/snooze/forget), retrieval health checks, dedup sweeps 201 ★
- Architecture Guardian — Use to verify MacMagazine module boundaries and system compliance are intact after adding/moving code or editi 169 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Impl Opus Medium
High-risk plan tasks - load-bearing invariants, the review path, architecture seams, shell entrypoints.
Doc Scout
Fetches official platform or vendor documentation for one load-bearing claim, as numbered facts with URLs.
Claim Extractor
Identify load-bearing claims in a draft report for verification against primary sources.
Mathlib Scout
Read-only Mathlib lemma/API finder for the lean-proof-agents repo. Given a goal or type pattern, returns a ran
Rs React Lint Format Check
Subagent of rs-school-react-pr-reviewer. Runs npm run lint and the Prettier check in a mentee's RS School Reac
Capability Reuse Auditor
Audits a proposed or just-authored new capability (a SKILL.md, an agent, or a packages/core module) for overla
Related Skills
Se Irr
Assumption Review — detect unproven assumptions, pin them in a commit-stamped record, promote the load-bearing
Skim Master Rules
Skim Master — output governance for AI agents. Nothing load-bearing is only in the middle: the first line alon
Draft Readable Rfd
When writing or editing an RFD README, apply three read-cold rules so a fresh reader can understand the docume