Path Prover — Development agent for Claude Code
Produces live evidence that every layer a lane touched actually works — boots the local stack or targets staging, drives the real path, and saves raw artifacts.
How to install Path Prover
Installs to ~/.claude/agents/vinipy12-lateralus-workflow-path-prover.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/vinipy12/lateralus-workflow/HEAD/agents/path-prover.md -o ~/.claude/agents/vinipy12-lateralus-workflow-path-prover.md Restart Claude Code, or start a new session, for it to be picked up.
What Path Prover does
name: path-prover description: Produces live evidence that every layer a lane touched actually works — boots the local stack or targets staging, drives the real path, and saves raw artifacts. Use before calling a lane done and before promoting a build. Reports what it observed; never judges whether the work is acceptable, never fixes anything. tools: Read, Grep, Glob, Bash model: sonnet effort: medium
You produce **evidence that the thing works**, in the environment asked for, and save
Alternatives in Development
- Harvest Curator — Draft session learnings from harvest staging into lizard-ready adoption notes 1k ★
- Browser Stealth Agent — Stealth browser automation agent for targets behind Cloudflare, Akamai, Google, DataDome, or PerimeterX bot de 812 ★
- Stimulus Agent — Creates accessible Stimulus controllers following Hotwire patterns with targets, values, and actions 652 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Corpus Prover
Proves a change on the maintainer's real local corpus — what number moved, by how much, and that nothing else
Harness Prover
Running-app verifier for harness eval loops. Drives the live feature (browser, API, or CLI) and returns a bina
Swift Staff Engineer
Senior iOS staff engineer reviewer. Use to critically review Swift implementation plans, architecture decision
Context Miner
Read-only review lane that mines organizational memory — git history of the touched paths, linked GitHub issue
Red Team Reviewer
Fresh-eyes adversarial review of the skill itself (not its outputs). Use before calling an iteration done, and
Coding Guidelines Reviewer
Use after finishing a change in this repo to check it against CODING_GUIDELINES.md's rigor tiers, the testing
Related Skills
Fleet Verify
Use after a UI or user-visible change and before you claim it works — it spawns ONE CCC verification lane that
Ix Plan
Generate a risk-ordered implementation plan for a set of targets. Assesses blast radius per target, finds data
Agency
Run a B2B task across three bounded agents (Analyst / SDR / Auditor). The in-lane agent produces work; the oth