rein-verify
25Skill Claude CodeCodex
Use before declaring code work complete. Runs verification, reviews diff hygiene, and emits an evidence report.
Skill Claude CodeCodex
Use before declaring code work complete. Runs verification, reviews diff hygiene, and emits an evidence report.
Cursor rule Cursor
Run a regression-tests-first cleanup/refactor workflow to reduce slop.
Cursor rule Cursor
Run one task through the full REIN flow from clarification through implementation, cleanup, review, and verification.
Cursor rule Cursor
Understand a codebase and maintain .rein/codebase/ as a navigable map with evidence-backed findings.
Cursor rule Cursor
Runtime-backed Socratic interview with durable state, clarity scoring, and spec bundle output.
Cursor rule Cursor
Use after triage, before implementation. Breaks complex work into sequenced steps with risks, checkpoints, rollback boundaries, and interview-result handoff support.
Cursor rule Cursor
Use after a miss, regression, or suspicious shortcut. Captures what failed and what rule should change.
Cursor rule Cursor
Use before committing. Self-reviews the current diff for unrelated changes, debug leftovers, test weakening, and scope drift.
Cursor rule Cursor
Use when requirements are too large, contradictory, or need negotiation. Produces a scope contract with what will and will not be done.
Cursor rule Cursor
Use before ambiguous or multi-file work. Surfaces relevant files, assumptions, success criteria, and cheating boundaries.
Cursor rule Cursor
Use before declaring code work complete. Runs verification, reviews diff hygiene, and emits an evidence report.
Instructions file CodexOpenCode
Instructions for jstxn/rein: Primary protocol: follow REIN.md. Companion protocol: use PRESSURE.md for regulated-pressure execution and evidence discipline. Precedence: if guidance overlaps or conflicts, REIN.md is the source of truth.
Agent Claude Code
Drafts PR titles, descriptions, and test plans from git diffs. Use when ready to open a PR.
Agent Claude Code
Explores codebases, gathers context, and investigates questions using read-only tools. Use for understanding code before making changes, tracing execution paths, or answering architectural questions.
Agent Claude Code
Reviews implementation against requirements, checks for correctness, edge cases, and consistency with project conventions. Use after completing a feature or fix.
Skill Claude CodeCodex
Read the latest review findings from .reviews/codex and .reviews/claude in the current git repository, combine them into a unified prioritized fix plan, and apply supported automatic fixes.
Skill Claude CodeCodex
Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.
Skill Claude CodeCodex
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.
Skill Claude CodeCodex
Always enforce a "repo rules + project memory" preflight before making code changes in any project. Use for virtually any implementation/debug/refactor/test task: first read applicable AGENTS.md (and any closer AGENTS.md for the touched directories) and .codex/memories/.md if present; otherwise read the project's…
Skill Claude CodeCodex
Run an automated, evidence-first review of current repository changes by scanning staged and unstaged diffs together, coordinating multiple review passes, and writing a combined findings report in .reviews/codex/YYYY-MM-DD-{iteration}.
Instructions file CodexOpenCode
AGENTS.md instructions for jstxn/agent-setup, covering global agent instructions, scope and precedence, preferred workflow, core principles and obsidian vault operations.
Instructions file CodexOpenCode
Instructions for jstxn/bebop, covering agent instructions: bebop, understanding your constraints, useful commands, helping users and creating and editing packs.