20,069 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Skill Claude CodeCodex
Run a complete Handover MCP continuity test across separate authenticated people or service agents. Use when asked to test an agent handoff end to end, qualify a Handover integration, verify multi-file round-trip, exercise revision-anchored review and correction, or test denied, read-only, stale-revision, and…
Skill Claude CodeCodex
Externally evaluates an already-implemented feature against its contract.md (environment, quality gates, coverage manifest, observable criteria), producing screenshots, a report, and chat findings. Owns the evaluation loop — keeps the attempt counter in progress.json, decides the state (CLEAN/FAIL/PENDING/ABORTED)…
Plugin Claude Code
Bundles 2 skills · 246 tokens together
Defense against LLM Rust failure modes: 59 categories of bugs that survive rustc, clippy, and cargo test — async cancellation, unsafe/FFI, concurrency, crypto, supply-chain, tests-that-pass-by-luck, semantic conformance, and systemic performance cost. Ships the rust-intel skill plus /rust-intel:audit, /rust-intel:fix.
Skill Claude CodeCodex
Standard operating procedure for an auditable, headless HEC-RAS workflow via the hec-ras MCP server — how to plan, copy, edit boundaries, run, QA-gate, read results, compare, plot, audit, and safely stop. Use FIRST whenever an agent is handed a HEC-RAS project (.prj folder) or a results file (.p##.hdf) plus a…
MCP server Claude CodeCodexCursor +2
MCP server "mcp-payment-safety-testbed" as configured in Saraid10/Trustgate. Runs locally from the mcp-payment-safety-testbed Python package.
MCP server Claude CodeCodexCursor +2
A CLI MCP server for ad-hoc UI testing of Android & iOS apps — a tight act+observe loop, device-condition control, log/crash & network capture, OCR targeting, accessibility audits, and session recording that exports a replayable flow. Runs locally from the manos-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "mcc-fleet" as configured in italoseara/mcc-fleet. Runs locally from the mcc-fleet Python package.
MCP server Claude CodeCodexCursor +2
Eyes for AI Agents — a machine-graded visual feedback loop coding agents consume to self-correct before claiming done. Runs locally from the agentvision Python package.
gautam-achieveai/ClaudePlugins
Plugin Claude Code
Bundles 15 skills, 2 commands, 5 agents, 3 hooks · 1,008 tokens together
Development methodology toolkit with Agile team delivery for large, long-horizon features. The agile-development skill coordinates thin end-to-end slices, durable progress state, early and continuous manual testing, observed-defect regression tests, behavioral tests for material acceptance contracts, final coverage…
Plugin Claude Code
Bundles 2 skills · 196 tokens together
Automatated testing framework.
Skill Claude CodeCodex
Iterative agent testing with session recovery. Execute, analyze, fix, resume from checkpoints. Use when testing an agent, debugging test failures, or verifying fixes without re-running from scratch.
Skill Claude CodeCodex
Project-local .cursor/skills/verify-templatebot drives the Vite marketplace over CDP; Feature Map includes 30-per-page D1 browse, browse card coat blend, unlisted /data analytics, PostHog funnel, marquee, pay-to-install, MCP publish, live X embeds, multi-bot collect progress/skip/claim + master-detail publish…
Cursor rule Cursor
JiraAgilePS project-wide development rules (Cursor entry point).
Plugin Claude Code
Bundles 4 skills · 1,782 tokens together
Pair or a team across Claude Code tabs — one driver does the task, integrates and reports; a navigator (pair) or one or more architects and one or more testers (team) review the plan before any work, approve the gated items, review the rest asynchronously and verify the result themselves. Each architect picks the…
Plugin Claude Code
Bundles 1 skill, 2 commands, 1 hook, 1 MCP server · 153 tokens together
Evolve skills, agents, prompts, code and plugins against examples with a parallel, merge-based optimiser.
Plugin Claude Code
Bundles 3 skills, 1 hook, 1 MCP server · 248 tokens together
A queryable map of your .NET test-automation solution for Claude: find existing steps before writing new ones, trace the blast radius of a change, and keep the map fresh. Needs the .NET 8 SDK and two global tools (dotnet tool install --global TestAtlas.Cli / TestAtlas.Mcp); the plugin tells you when they are missing.
Plugin Claude Code
Bundles 1 skill · 245 tokens together
Finds the engineering controls your repository does not have — CI that never runs on pull requests, a check target that quietly rewrites files, a migration with nothing in front of it — and hands back a numbered plan. Advisory: it changes nothing until you pick.
Skill Claude CodeCodex
Write, validate and archive OpenSpec specs (konvoy-delivery schema); map screens, convert docs, draft specs from code, triage drift. Use before code for a feature or unclear task.
Skill Claude CodeCodex
Execute written browser test scenarios (smoke, regression, or ad-hoc numbered steps) against a live web app with a Playwright browser MCP server, then report a per-step PASS/FAIL table with evidence and a root-cause verdict. Use when asked to "run the smoke suite", "run regression", "run scenario AUTH-1", "test this…
Skill Claude CodeCodex
Delegate coding questions, code reviews, test generation, refactoring suggestions, or second opinions to external LLMs (NVIDIA NIM, OpenRouter, Groq, DeepSeek, or a local Ollama) with zero dependencies. Use this skill whenever the user asks for another model's take, an independent review, a senior-engineer-style…
Skill Claude CodeCodex
Develop, test, and publish tunnel-manager without breaking its typed SSH inventory, remote-execution, MCP action, packaged-content, spec-dashboard, or governed Pages contracts. Use when changing connector code, docs, skills, workflows, or repository-owned specifications.
Skill Claude Code
A pre-send evaluation check for changes to email recipients, addresses, or message text. It compares the change with a dataset that defines when sending is allowed.
Skill Claude Code needs its repo
Use ao relatar defeito em sistema que já existe: não funciona como deveria, não segue o padrão esperado, trava, some ou dá valor errado — mesmo sem a palavra bug. Inclui falha de interface e interação (arrastar, clicar, salvar) e ajuste de tela, cálculo ou campo. Feature nova é sprintx.
MCP server Claude CodeCodexCursor +2
Agent-built web app quality gate. Real browser is the judge. PASS/FAIL with receipts. Runs locally from the dsh-verify npm package.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: