Agent Workflows · Debugging

Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

obra/superpowers

Reach into past AI conversation history through the trellis mem CLI.

mindfold-ai/Trellis

Runs an autonomous modify, verify, keep-or-discard loop against any metric, with subcommands for planning, debugging, fixing, security audits, shipping and more.

uditgoenka/autoresearch

Answers questions about a past agent run from its recording, using causal graphs and replay, instead of reconstructing events from memory.

iflytek/skillhub

Pushes an agent to exhaust every option, investigate before asking and take initiative beyond the literal request, instead of giving up or waiting passively.

tanweai/pua

Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.

mindfold-ai/Trellis

Diagnoses surprising LoopX behavior, such as stale recommendations or tiny progress, assigns it to the responsible layer and repairs it at the lowest durable level.

loopx-project/loopx

Diagnoses and repairs a broken AutoRAG install so every configured datasource is both indexed and returns real search hits.

Marker-Inc-Korea/AutoRAG

Gives an agent a set of working rules for any development task: understand first, surface decisions, verify results, and load deeper reference files per scenario.

shareAI-lab/Kode-CLI

Has Leon's agent investigate, change and verify code in a repository with its file, search and shell tools, staying inside the scope the owner authorized.

leon-ai/leon

Researches code with evidence: traces callers, imports and cross-repo links, diagnoses failures and reports findings with exact file and line references and a confidence label.

bgauryy/octocode

Search and record failure-recovery lessons from real engineering sessions; submit and verify debugging lessons across the MisakaNet network.

Ikalus1988/MisakaNet

Run, test, and debug the photofield server locally. An agent skill from SmilyOrg/photofield.

SmilyOrg/photofield

Embedded hardware debugging workflow for probe-rs targets using embedded-debugger-mcp.

Adancurusul/embedded-debugger-mcp

Debug and trace ColecoVision and Super Game Module games using the Gearcoleco emulator MCP server.

drhelius/Gearcoleco

A skill your agent uses when investigating a bug, failing test, or unexpected runtime behavior and the mcp-debugger MCP server is available — drives real step-through debuggers (breakpoints, stack…

debugmcp/mcp-debugger

Diagnoses a recurring failure such as a stuck task, repeated CI error or frequent reverts by sending sub-agents through the logs and returning one root-cause diagnosis.

yologdev/yoyo-evolve

Runs a reference agent (Codex or Claude Code) and Qwen Code on the same scenario, captures HTTP and terminal traces, and compares them until behavior matches.

QwenLM/qwen-code

Diagnoses a Muse Code installation's own failures from binary and session evidence, instead of treating the report as an ordinary repository bug.

asgeirtj/system_prompts_leaks

Guidance for writing, editing, reviewing, and debugging JavaScript workflow code for pi-dynamic-workflows.

QuintinShaw/pi-dynamic-workflows

Pushes an agent that keeps failing or gives up to exhaust every option, using harsh corporate-pressure wording, a diagnosis line and a proactivity checklist.

tanweai/pua

Guidelines and step-by-step workflow for debugging DevTools extensions locally, including stub mode, fixed-port launching, browser auto-opening, URL query parameters, target app connection, and…

flutter/devtools

A skill your agent uses when the user asks to take a feature or bug fix from prompt to implementation, especially prompts like "/create a new feature", "build this feature end-to-end", "take this…

zacharyfmarion/openscad-studio

Autonomous local-development debugging loop for Helmor bugs.

dohooo/helmor

Checks and tunes token-saver output compression: reads stats, explains why a command was or was not compressed, and edits config files or environment variables.

ppgranger/token-saver

Apply cognitive constraints that reshape thinking. An agent skill from NeoVertex1/context-field.

NeoVertex1/context-field

Run the infrastructure health check and fix anything that fails

diet103/claude-code-infrastructure-showcase

Orchestrate complex Codex coding work for the Plus profile with GPT-6 Luna at max reasoning as planner/integrator, Luna subagents for exploration, implementation, testing, and research, and an Astra…

donvito/codex-astra-luna-orchestrator

Create, manage, and debug Claude Code Agent Skills. An agent skill from seasonedcc/remix-forms.

seasonedcc/remix-forms

Teaches an agent to inspect Open-Science's JavaScript control REPL, check which host.* calls are allowed, and find project files, sessions and agent frames.

aipoch/open-science

Pushes an agent that keeps failing, gives up or claims unverified success into a diagnosis, evidence and verification loop, with a Pi extension for persistent mode.

tanweai/pua

Query and write durable debugging memory recorded by MemoryWhale.

wuisabel-gif/MemWhale

Diagnoses misbehaving ADK agents by inspecting sessions, events, tool calls, and the exact request that reached the model.

google/adk-python

Orchestrate complex Codex coding work for the Pro profile with GPT-6 Astra at medium reasoning as planner/integrator, Luna subagents for exploration, implementation, testing, and research, and an…

donvito/codex-astra-luna-orchestrator

Systematic hook debugging workflow. An agent skill from parcadei/Continuous-Claude-v3.

parcadei/Continuous-Claude-v3

Interactive debugging mode that generates hypotheses, instruments code with runtime logs, and iteratively fixes bugs with human-in-the-loop verification.

doraemonkeys/claude-code-debug-mode

Operate, reproduce, and debug a running local Helmor desktop development build through the Tauri MCP bridge.

dohooo/helmor

An instruction-only discipline for Trae that forces evidence-based work when an agent keeps failing, gives up or declares a task finished without proof.

tanweai/pua

Locks file edits for the session to one directory by blocking Edit and Write calls anywhere else, useful when debugging or scoping a change.

garrytan/gstack

Plan a py4vasp change as an ordered list of test-first chunks — that chunk list is the plan.

vasp-dev/py4vasp

Explore user intent, requirements, and design options through collaborative dialogue before implementation.

feiskyer/claude-code-settings

Launch a Qualitative Neural Network (QNN) — a layered, multi-epoch brainstorm of agent personas that maps divergent strategies before implementation.

iblameandrew/open-deepthink

Scope definition before implementation — two modes. An agent skill from AlexZio00/sovereign-skills.

AlexZio00/sovereign-skills

MCP Protocol Inspection and Debugging with Inspector CLI. An agent skill from adeze/raindrop-mcp.

adeze/raindrop-mcp

Runs cozempic doctor to check Claude Code configuration and sessions for known problems such as trust-dialog hangs, corrupted tool blocks and zombie teams.

Ruya-AI/cozempic

Systematic debugging with persistent state across context resets

SpillwaveSolutions/agent-brain

Create a new task in the Bernstein orchestrator. An agent skill from sipyourdrink-ltd/bernstein.

sipyourdrink-ltd/bernstein

VSCode MCP Bridge project architecture — current monorepo layout, IPC/EventDispatcher flow, per-workspace socket discovery, MCP/CLI adapters, tool filtering, and VSCode extension services.

tjx666/vscode-mcp