Command Claude Code
Commit, push, and open a PR. Branch rules prevent accidents on main or duplicate PRs.
2 21d ago A 0 tokens
original MIT
Command Claude Code
Generate a PR description from the diff. Triggered when a whitelisted author puts @elixpoo fill in the PR body.
2 21d ago A 0 tokens
original MIT
Command Claude Code
Respond to an issue triggered by @elixpoo mention or the ELIXPO label.
2 21d ago A 0 tokens
original MIT
review
04Command Claude Code
Command "review" from elixpo/claudeOps.elixpo, covering what to look at, don't, output format, issues and suggestions.
2 21d ago A 0 tokens
original MIT
Instructions file CodexOpenCode
Instructions for elixpo/claudeOps.elixpo, covering agent guidelines for claudeops.elixpo, architecture, repository structure, hard constraints and git & pr workflow.
2 21d ago A 599 tokens
original MIT
Instructions file
Instructions for elixpo/claudeOps.elixpo: See AGENTS.md for the operating manual — architecture, conventions, and common mistakes.
2 21d ago A 87 tokens
original MIT
architect
07Agent
System architecture specialist for design decisions, ADRs, and technical trade-offs. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions. Never writes implementation code.
2 21d ago A 42 tokens
copy · 100% MIT
brancher
08Agent
Explores multiple solution approaches before committing to one. Use proactively for algorithm selection, data structure choices, or any decision where 3+ fundamentally different approaches exist.
2 21d ago A 35 tokens
copy · 97% MIT
breaker
09Agent
Adversarial code reviewer that tries to break code. Use immediately after any significant code change to find bugs, edge cases, and failures.
2 21d ago A 30 tokens
copy · 98% MIT
Agent
Visual design reviewer that critiques UI output. Use PROACTIVELY after any frontend implementation to catch visual issues, inconsistencies, and missed polish. Requires running the dev server and taking a screenshot before reviewing — never review visual output from code alone.
2 21d ago A 53 tokens
copy · 100% MIT
fuzzer
11Agent
Generates property-based tests that find edge cases humans miss. Use for pure functions, parsers, serializers, data transformations, and any code where input space is large.
2 21d ago A 37 tokens
copy · 97% MIT
judge
12Agent
Evaluates multiple competing solutions and selects the best one. Use after parallel worktree racing or when multiple approaches exist. Judges on correctness, complexity, testability, and maintainability.
2 21d ago A 38 tokens
copy · 95% MIT
prism
13Agent
Parallel bias-isolated review with 4 specialized single-domain reviewers (security, performance, test coverage, correctness). Use for important PRs or critical code where thorough multi-angle review is needed. Each perspective has blinders — forces deeper analysis per domain.
2 21d ago A 53 tokens
copy · 94% MIT
questioner
14Agent
Mandatory pre-implementation interrogation. Use before any non-trivial coding task to surface assumptions, find existing solutions, and prevent over-engineering. Forces 6 critical questions before a single line of code.
2 21d ago A 43 tokens
copy · 91% MIT
red-team
15Agent
Security red team specialist. Attacks the developer's stated security assumptions. Use proactively when code touches auth, billing, API, or infrastructure.
2 21d ago A 31 tokens
copy · 100% MIT
refiner
16Agent
Multi-pass self-review that forces write-critique-rewrite-verify cycle. Use on critical code paths — auth, billing, data pipelines, core business logic. Catches issues single-pass review misses. Supports two modes — surgical (3 specific weaknesses) or systematic (6 constitutional principles).
2 21d ago A 61 tokens
copy · 95% MIT
researcher
17Agent
Multi-depth research agent with configurable intensity. Use for any research task — from quick lookups to nuclear-level exhaustive investigations. Specify depth in the prompt: surface, basic, deep, in-depth, ultra, nuclear, overkill.
2 21d ago A 49 tokens
copy · 86% MIT
specwriter
18Agent
Pre-implementation requirements interviewer. Use BEFORE any non-trivial feature, refactor, or new project. Reads the codebase, asks 20-40 probing questions in structured rounds, and produces a bulletproof SPEC.md with testable acceptance criteria, exact files to modify, and a wiring checklist. Never writes…
2 21d ago A 68 tokens
copy · 100% MIT
test-auditor
19Agent
Detects fake, theatrical, and meaningless tests. Use PROACTIVELY after test suites are written to catch mock-everything tests, tautological assertions, happy-path-only coverage, and tests that pass but verify nothing. The anti-"test theater" agent.
2 21d ago A 58 tokens
copy · 98% MIT
ui-architect
20Agent
Frontend UI/UX design specialist. Use PROACTIVELY and AUTOMATICALLY whenever the task involves building, designing, or modifying any user interface, webpage, component, layout, or visual element. This includes React, Next.js, Vue, Svelte, HTML/CSS, Tailwind, or any frontend framework.
2 21d ago A 68 tokens
copy · 100% MIT
wirer
21Agent
Verifies that new code is actually wired into the running system — not orphaned. Use PROACTIVELY after any implementation to catch dead code, unregistered routes, unrendered components, and disconnected modules. The.
2 21d ago A 47 tokens
copy · 95% MIT