Debugging agents

AlexPEClub/ai-coding-starter-kit

Agent Claude Code

Tests features against acceptance criteria, finds bugs, and performs security audits.

apmantza/pi-lens

Agent Claude Code

Log-forensics and root-causing for pi-lens runtime behavior — inconclusive rates, stale findings, silent degradations, crash attribution, dogfood-session anomalies. Use when the question is "what actually happened and why", not "apply this fix". Spawn with the symptom (quotes, timestamps, session context) and the…

magnusoverli/opencode

Agent

Investigate and diagnose Home Assistant with no ability to change anything. Reads configuration, queries live state, history and logs, and ends with findings and a recommendation. Cannot edit files, run shell commands, call services, write configuration, or spawn subagents.

OpenSource03/harnss

Agent Claude Code

Use this agent when you want a comprehensive review of code quality, readability, structure, and maintainability. This agent focuses on how well-written and organized code is — not on bugs, logic errors, or functional correctness. It examines file length, function complexity, naming conventions, code organization…

0xquinto/bcherny-claude

Agent Claude Code

You are an on-call support specialist. Help diagnose and resolve production issues quickly.

EXXETA/exxperts

Agent

Code review specialist for quality and security analysis.

EXXETA/exxperts

Agent

Fast codebase recon that returns compressed context for handoff to other agents.

griddynamics/rosetta

Agent

Generalized reusable lessons from agent sessions. Root causes converted into preventive rules, not incident-specific notes. Entries are h3 headers with [ACTIVE|RETIRED] status. Content: brief, grep-friendly, MECE across sections. Style: one-liner per entry, optional sub-bullets for context.

TheRealSavi/iOpenPod

Agent

Use uv for every Python command in this repo. Do not use bare python, pip, poetry, or conda.

VasiHemanth/tokentelemetry

Agent Claude Code

Deep single-subsystem audit that reasons about state over time (caches, upserts, migrations, concurrent scans) rather than pattern-matching lines. Used by /bug-audit on the riskiest subsystems; runs on Opus for reasoning depth.

VasiHemanth/tokentelemetry

Agent Claude Code

Fast, wide sweep of one audit dimension across the codebase. Returns candidate findings with file:line evidence for the verifier to confirm. Used by /bug-audit; runs on Sonnet for breadth per token.

VasiHemanth/tokentelemetry

Agent Claude Code

Adversarially verifies one candidate finding from /bug-audit — tries to REFUTE it by reading the code and, where cheap, reproducing it with a throwaway script. Kills false positives before they reach the report. Runs on Opus.

Southclaws/storyden

Agent Claude Code

Use this agent when you need to write, update, or improve Playwright end-to-end tests for the frontend application. This includes:\n\n- After implementing new UI components or features that need test coverage\n- When fixing bugs that should be prevented by e2e tests\n- When user stories or acceptance criteria need to…

devswha/patina

Agent

Triggers when Claude needs to find AI-writing patterns or suspect zones in KO/EN/ZH/JA text. Use this agent to run a full detection pass — pattern scanning across all applicable packs, stylometric analysis (burstiness CV + MATTR + AI-lexicon density), and Korean diagnostic signals — and receive a structured…

scrypster/muninndb

Agent Claude Code

Tries to break things, under one evidence standard: a finding is executable or it is not a finding. Two modes. REFUTE — given a change or a design, find the input, ordering, crash point, concurrent caller, or false premise that makes it wrong. PROOF — given a claim ("this bug exists", "this fix works"), reproduce the…

2anki/2anki.net

Agent Claude Code

Implements features and bug fixes for 2anki/server. Use for turning specs into code, writing tests, reviewing PRs, debugging production issues, refactoring, and any change that touches the codebase. Takes a spec or issue, produces working code with tests, opens a PR.

PlayableIntelligence/game-creator

Agent

Runs Playwright test suites for browser games, diagnoses failures, fixes game code, and re-runs until green. Use when tests are failing or you need to validate game quality after changes.

oxbshw/watch-skill

Agent

Agent "aider" from oxbshw/watch-skill, covering watch skill in aider, install, use it, a recording of a bug and notes.

InterfaceX-co-jp/genshijin

Agent

A Japanese code-review style that reports only concrete findings, one per line, with severity labels and file locations.

Adityaraj0421/naksha-studio

Agent

Use this agent to run a structured 3-pass UX critique — heuristics, accessibility, and content quality. Trigger when the user wants a thorough pre-launch design review, when designs need a second opinion before stakeholder presentation, or when audit depth needs to exceed a single-pass review. Context: User wants a…

SchroederNathan/clarity

Agent

Logic, correctness, and code-quality bugs in the changed code (off-by-one, bad error handling, type-safety gaps, unsafe assumptions).

Fu-Jie/openwebui-extensions

Agent

The single top-level entry point for ALL tasks in openwebui-extensions. Covers the complete project lifecycle: new plugin scaffolding, feature development, testing, documentation, release, issue triage & reply, community announcements, and self-learning. Routes to the right agents and skills in parallel or…

Fu-Jie/openwebui-extensions

Agent

End-to-end plugin testing agent for OpenWebUI. Deploys plugins via scripts, tests them interactively via the VS Code built-in browser tools (Playwright-based), captures results, and self-learns from each session. Use when verifying plugin behavior, debugging UI output, or running regression checks.

ai-analyst-lab/ai-analyst

Agent

Agent "hypothesis" from ai-analyst-lab/ai-analyst, covering agent: hypothesis forming, purpose, inputs, workflow and step 1: parse the question brief.