Agent Claude Code
Validates that the project builds, lints, type-checks, and tests pass. Supports a --deep mode for full install + sequenced test run.
2 8d ago A 35 tokens
original MIT
Agent Claude Code
Reviews code changes from a staff engineer perspective — architecture, patterns, and trade-offs.
2 8d ago A 21 tokens
original MIT
Agent Claude Code
Deep scan a folder for bugs — logic errors, race conditions, SQL issues, assertion gaps.
2 8d ago A 25 tokens
original MIT
oncall-guide
04Agent Claude Code
Diagnose test or CI failures by analyzing logs, errors, and recent changes.
2 8d ago A 20 tokens
original MIT
Agent Claude Code
Critiques an implementation plan before any code is written — finds missing edge cases, wrong layering, and scope creep.
2 8d ago A 27 tokens
original MIT
Agent Claude Code
Stacked-PR helper — inspects gh-stack state, proposes the next safe action, and summarises where you are.
2 8d ago A 29 tokens
original MIT
acp
07Command Claude Code
Stage all changes, create a commit with a descriptive message, and push to the remote. Stack-aware.
2 8d ago C 0 tokens
original MIT
Command Claude Code
Hand this session off to Codex — or pull Codex's work back into Claude. One command, both directions.
2 8d ago B 0 tokens
original MIT
dave
09Command Claude Code
Get a second opinion on the current change or plan from Dave AI (Alteos-internal assistant) via the dave CLI. Single round — Dave's reply is rendered back verbatim, then Claude follows up with its own evaluation.
2 8d ago C 0 tokens
original MIT
grill
10Command Claude Code
Grill the current changes before they become a PR. Fan out independent reviewers to attack your diff from every angle.
2 8d ago A 0 tokens
original MIT
plan
11Command Claude Code
Draft an implementation plan, grill it with independent adversarial reviewers, and — once the user approves — save the refined plan as a checked-in artifact that rides with the stacked PRs.
2 8d ago A 0 tokens
original MIT
rabbit
12Command Claude Code
Run CodeRabbit review on the current branch against the repo's default branch.
2 8d ago A 0 tokens
original MIT
scan
13Command Claude Code
Deep-scan a folder for real bugs using the deep-bug-scan agent.
2 8d ago A 0 tokens
original MIT
stack
14Command Claude Code
Manage a stacked-PR workflow using GitHub's gh stack extension.
2 8d ago A 0 tokens
original MIT
techdebt
15Command Claude Code
Find and remove duplicated logic, dead code, and low-value abstractions across the whole repo (use the built-in /simplify skill instead if you only want to clean up the current diff). Run this at the end of a session to keep tech debt from accumulating.
2 8d ago A 0 tokens
original MIT
verify
16Command Claude Code
Pre-PR verification gate. Runs the project's checks and hands off to diagnosis on failure.
2 8d ago A 0 tokens
original MIT
PostToolUse
17Hook Claude Code
Runs after a tool call finishes for Write and Edit tool calls, executing format-on-write.sh. From cbmono/ai-setup.
2 8d ago A
tokens not measured
original MIT
ai-setup
18Settings file Claude Code
Agent settings declaring 1 hook event (PostToolUse) and 82 allowed tools.
2 8d ago E
tokens not measured
original MIT
Skill Claude CodeCodex
Use when building or editing frontend UI — components, pages, forms, buttons, links, inputs, modals, or any interactive/asserted element. Adds stable test locators (data-testid / data-test) and accessibility handles so E2E tests don't go flaky.
2 8d ago A 59 tokens
original MIT
Instructions file
Instructions for cbmono/ai-setup, covering claude.md, what this repo is, this repo owns /.claude, layout and commands vs skills.
2 8d ago A 4,493 tokens
original MIT