Debugging

airfloats/gdb_mcp

MCP server Claude CodeCodexCursor +2

MCP server "gdb-mcp-server" as configured in airfloats/gdbmcp. Runs locally from the gdb-mcp-server Python package.

tokyubevoxelverse/fence

Skill Claude CodeCodex

Investigate why a strange piece of code exists before anyone deletes it (Chesterton's fence). Use when the user points at a weird line, hack, magic constant, or workaround and asks why it's there, whether it's still needed, or if it's safe to remove.

zavora-ai/skill-test-execution

Skill Claude Code

Orchestrate test execution — run unit, integration, and E2E tests, collect coverage reports, and analyze failures. Use when running tests, checking coverage, debugging test failures, or validating code changes before merge.

adityaarakeri/senior-agent-skills

Skill Claude CodeCodex

Thoroughly find dead, unused, and unreachable code in a repository and produce a confidence-ranked report. Use this skill whenever the user asks to find dead code, unused variables, unused functions or classes, unreachable code, orphaned files, unused exports, unused dependencies, stale CI files, orphaned config…

javi22020/ralph

Agent Claude Code

Triage a stuck Ralph loop and propose either a revised fix plan, a specific question to ask the user, or a recommendation that the task is infeasible. Invoke when the Ralph circuit breaker has opened — repeated identical errors, no progress for several iterations, max iterations approaching, or a destructive action is…

tokyubevoxelverse/checkup

Skill Claude CodeCodex

Give a repository a full health exam — doc rot, dependency staleness, CI decay, git hygiene, dead links, docs contradicting code — and grade it. Use when the user wants to know what quietly rotted, or a prioritized maintenance list.

ukkuru/testmetry-skills

Skill Claude Code

Use when someone asks to analyze a defect report, analyze bug data, perform defect metrics analysis, review a defect log, or upload a defect file for quality insights.

zavora-ai/skill-observability-monitoring

Skill Claude Code

Orchestrate full-stack observability — query logs, search traces, monitor metrics, manage alerts, handle incidents, track SLOs, and execute runbooks. Use when debugging errors, investigating latency, checking service health, managing alerts, responding to incidents, reviewing SLO burn rate, or finding runbooks.

Howell5/willhong-skills

Skill Claude CodeCodex

A code-reduction audit method for finding unused code, duplicate implementations, unused dependencies, and unnecessary generalisation. It also creates automated checks to prevent a codebase from growing without need.

valarpirai/code-graph

Skill Claude Code

Query the Code Graph knowledge graph for this codebase. Use when the user asks about code structure, call relationships, dependencies, blast radius, or wants to run SPARQL queries against the project graph. Requires the backend and MCP server to be running.

codepros100-dev/claude-windows-health-check

Skill Claude Code

Comprehensive Windows system health check, diagnostics, and remediation.

marky291/claude-drift

Plugin Claude Code

Bundles 1 skill, 2 agents · 243 tokens together

Detects and fixes drift between a project's Claude artifacts (CLAUDE.md, skills, commands, agents, hooks/settings, and native/MCP memory) and the project's actual current reality: broken references, stale context, and legacy-narration framing that should read forward-looking.

sanjeewamadhuranga/grounding-guard

Plugin Claude Code

Bundles 2 skills, 2 hooks · 79 tokens together

Hook-enforced ground-truth verification for Claude Code. Catches fabricated package names, unpublished versions, unresolvable imports, and nonexistent git SHAs before they land in your codebase — and feeds the correction back to Claude so it fixes itself in-loop.

BekbolotM/repo-doctor

Plugin Claude Code

Bundles 1 command, 6 agents · 199 tokens together

Full health checkup for any repository: Health Score 0-100, findings across 5 dimensions (security, code quality, testing, production readiness, docs), a prioritized fix plan, and one-command fixes with /audit fix N.

takoyaro/the-agency

Agent Claude Code

Root-cause investigator. Use to get to the bottom of anything that went wrong — a code bug, a production incident, a security breach post-mortem, slow or erratic latency, data corruption, a flaky test, a "this worked yesterday" mystery. Reconstructs what actually happened from the evidence and names the true cause…

tslateman/duet

Plugin Claude Code

Bundles 27 skills, 6 commands, 1 agent · 1,236 tokens together

Claude Code plugin for reflection, code quality, writing, and design.

gul-labs/craftsman-marketplace

Plugin Claude Code

Bundles 12 skills · 1,830 tokens together

Ship something with Lovable, Replit, Bolt, v0, Claude Code, or Codex and it works, but nobody with an engineering background has checked it. This is the engineering review you'd get from the technical co-founder you don't have. craft-audit checks the whole project across ten areas: UX, frontend, backend, database…

debabsah/fable-method

Plugin Claude Code

Bundles 7 skills, 1 agent, 2 hooks · 582 tokens together

Installs 'The Fable Way' working discipline, built for a frontier Claude model at medium-xhigh effort: an auto-triggering method skill (reflexes, risk tiers, plan shape, a calibrated-code stance) plus runner skills (scope, debug, adversarial review, verify, ship) that dispatch a capability-confined fable-lens reviewer.

keez97/phase-gate

Plugin Claude Code

Bundles 4 commands, 3 agents · 320 tokens together

Plan → implement → validate → adversarial debug-sweep loop, linked by a verification.jsonl artifact.

dlebed/python-clang-mcp

Plugin Claude Code

Bundles 1 MCP server

C/C++ code introspection via libclang — fills gaps that clangd-via-LSP cannot expose (macro expansion at use-site, record layout, predicate-based AST queries, bitfield audits, attribute audits, call-site argument patterns).

vonargo/intelaisense

Plugin Claude Code

Bundles 1 skill, 2 hooks · 27 tokens together

A perception layer for AI coding agents: ambient, on-write signals (staleness, diagnostics, blast-radius) pushed into context via one dispatcher hook.

afaraha8403/balakit

Skill Claude Code

Evidence-driven dissection of an existing service, written plan, or codebase area. Interrogates every entity (table, field, component, endpoint, module, boundary) against ground truth from multiple sources at once, red-teams each verdict devil's-advocate style, and arrives at the minimal-build optimization plan. Runs…

IyedNasra/skeptic

Skill Claude CodeCodex

Use when debugging failures, writing tests, starting multi-step tasks, modifying build systems, integrating APIs, or validating assumptions before heavy execution.

soleimanmansouri/debug-bank

Skill Claude CodeCodex

Fallback debugging when no pattern matches — hypothesis-driven code instrumentation with auto pattern extraction.