DebugPro
codexEvidence-first debugging for Codex.
21 skills · 2 agents
Codex Chrome DevTools plugin with route sessions, upstream MCP delegation, live evidence bundles, API discovery, redacted cURL, performance workflows, and sync guardrails.
Plugin chrome-devtools from marketplace toolihan in therealityreport/toolihan. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
chrome-devtools-accessibilityUse when debugging page accessibility with @ChromeDevTools, including Lighthouse accessibility audits, accessibility tree snapshots, semantic HTML, ARIA labels, form labels, focus order, keyboard navigation, tap targets, color contrast, and document-level accessibility checks.
chrome-devtools-evidenceUse when ordering browser debugging evidence into a timeline, comparing debug runs, summarizing screenshots or console entries, collecting live evidence bundles, and preserving redaction warnings.
chrome-devtools-extension-healthUse when checking Chrome DevTools bridge health, extension readiness, adapter boundaries, and upstream route readiness without installing or mutating browser extensions.
chrome-devtools-intakeUse when starting a Chrome DevTools debugging run, selecting a safe target preview, gathering user-visible symptoms, and choosing fixture, isolated live route, or profile-connected route evidence.
chrome-devtools-memoryUse when investigating browser memory growth with @ChromeDevTools, including suspected JavaScript memory leaks, OOM symptoms, heap snapshots, detached DOM nodes, closure leaks, event listener leaks, unbounded client caches, and bounded upstream heap comparison, filters, retainers, dominators, edges,
chrome-devtools-networkUse when analyzing fixture, dry-run, or gated upstream network evidence, API Discovery Workbench output, redacted cURL commands, response metadata, and bounded response body handling.
chrome-devtools-performanceUse when choosing Lighthouse, performance traces, or both, and when summarizing fixture or gated upstream performance evidence.
chrome-devtools-repair-loopUse when applying the bridge doctor and repair loop for Chrome DevTools debugging, including Context7 docs checks, upstream MCP gates, route-session failures, and small evidence-backed fixes.
chrome-devtools-runtimeUse when grouping console, runtime, framework, and source-correlation evidence into actionable error fingerprints for fixture, dry-run, or gated upstream debugging.
chrome-devtools-api-workbenchchrome-devtools-bridge-doctorchrome-devtools-live-session-doctorchrome-devtools-network-analystchrome-devtools-performance-analystchrome-devtools-sync-doctorchrome-devtools-triageecho "@ChromeDevTools: startup drift check is available for install/cache/marketplace sync state."
sh -lc 'root="${CODEX_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}"; [ -z "$root" ] || node "$root/scripts/codex-startup-check.mjs"'
Evidence-first debugging for Codex.
21 skills · 2 agents
Decodo scraping, proxy, MCP, and SDK workflows for Codex.
9 skills · 6 agents · 1 MCP server
Find, compare, improve, self-check, and plan installation for agent tools across callable Codex tools, connector plugins, local inventory, live GitHub, Hugging Face, skills.sh, npm, Python, Homebrew, and deferred package registries.
13 skills
Current library documentation lookup through a capability-preserving Context7 MCP proxy, CLI workflows, skills, and a focused docs researcher agent.
7 skills · 1 agent · 1 MCP server
Audits a frontend project against the 30 Laws of UX (lawsofux.com). Detects the UI stack, scores each applicable law from concrete source-code signals, and produces a graded report (0-100 + A-F) with a findings table, a coverage band, and a prioritized quick-wins-vs-larger-efforts fix list. Static by default; an optional --url pass measures the running app. Read-only unless you run /ux-fix.
1 skill · 3 commands · 2 agents
Multi-page HTML explainer/guide generator. Builds styled, multi-tab HTML docs into the knowledge-base, creates last-30-days community pulse docs, routes optional external tools, previews through Playwright MCP, renders diagrams/charts, and registers docs in the library index.
2 skills · 2 commands · 1 MCP server
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.