Testing agents

gotgenes/pi-packages

Agent

Fresh-context craftsmanship scout — reads the largest test files and sweeps method-level design, naming, and test-code quality into a scored debt inventory for phase planning.

gotgenes/pi-packages

Agent

Fresh-context quality reviewer — runs deterministic checks and judgment checklist before handoff to /ship-issue.

techygarg/lattice

Agent

Part of lattice

Runs a project's configured verification stages (build/unit/integration/etc.) from .lattice/verification.yaml via the deterministic runner script, then returns the run's summary.json verbatim. Invoke before declaring work done, to confirm a change actually works, or whenever a faithful execution report is needed…

techygarg/lattice

Agent

Part of lattice

Why the verifier exists, the cost model behind it, and how to wire it into your own sessions.

BugTraceAI/BugTraceAI-CLI

Agent

The IDOR Agent (Insecure Direct Object Reference) is a specialist agent in BugTraceAI that detects and exploits IDOR vulnerabilities. It uses a WET→DRY two-phase pipeline with LLM-powered deduplication and optional deep exploitation analysis.

nesquikm/mcp-rubber-duck

Agent Claude Code

Use this agent when you need to test, debug, or validate LLM provider configurations. This includes verifying API keys work correctly, checking provider connectivity, testing model availability, debugging authentication issues, validating base URLs for custom providers, or troubleshooting why a specific provider isn't…

TechDufus/oh-my-claude

Agent

Part of oh-my-claude

Mission-first validator that runs relevant checks, reports evidence, and returns a binary pass/fail verdict with next steps.

jmckinley/claude-code-resources

Agent

Runs tests and provides detailed failure analysis.

al3rez/ooda-subagents

Agent Claude Code

OODA Act phase - Implements the decided solution with precision, tests thoroughly, and validates results.

tettethu/VibeGame

Agent

Runtime verification teammate for one code task. Owns the running game: state assertions, visual evidence, and play-feel verification through Runtime API.

animeshkundu/youtube-audio

Agent

Testing and QA expert for YouTube Audio (Vitest unit tests + hermetic Selenium bench).

devlint/GitWand

Agent Claude Code

Adversarially verifies a GitWand change before PR — runs the test suites, checks AGENTS.md compliance, and reviews the diff. Read-only (no Edit/Write) so the review stays honest. Use after the executor finishes, before opening a PR.

softspark/ai-toolkit

Agent

Part of app

MCP protocol testing expert. Use for MCP server testing, protocol compliance, transport validation, integration testing. Triggers: mcp test, protocol compliance, mcp validation, transport testing.

ascend-ai-coding/awesome-ascend-skills

Agent Codex

Compare two outputs WITHOUT knowing which skill produced them.

ascend-ai-coding/awesome-ascend-skills

Agent Codex

Evaluate expectations against an execution transcript and outputs.

AgriciDaniel/skill-forge

Agent

Part of skill-forge

Blind comparison agent for A/B testing skill versions. Evaluates outputs from two skill versions without knowing which is "new" vs "old" to eliminate bias. User says: "compare these two skill versions" User says: "run a blind A/B test on the skill".

vericontext/vibeframe

Agent Claude Code

End-to-end tester for the current VibeFrame CLI. Use when asked to test everything, run full tests, or verify the repo works.

smixs/skill-conductor

Agent

Part of skill-conductor

Evaluate a skill artifact with atomic binary yes/no questions, one answer (1/0) per question, each preceded by a written critique grounded in evidence from the skill's own files. Aggregate to per-dimension scores in [0,1]; the orchestrator turns your answers into the overall score and the pass/fail gate.

smixs/skill-conductor

Agent

Part of skill-conductor

Evaluate expectations against an execution transcript and outputs.

outlmd/outl

Agent Claude Code

Validates that changes in outl-core preserve the tree CRDT invariants (convergence, idempotency, no-cycle, no-silent-loss). Use PROACTIVELY after any edit in crates/outl-core/src/tree.rs, log.rs, op.rs, or in tree CRDT tests. Rejects PRs that break any invariant.

outlmd/outl

Agent Claude Code

Ensures that the .md ↔ ops ↔ .md pipeline is stable and that blocks never disappear silently during external matching. Use PROACTIVELY after changes in outl-md (parse, render, sidecar, matching). Runs roundtrip + matching suite and reports divergences.

workersio/skills

Agent

Part of wio

Read-only WIO subagent for discovering high-value test or workload candidates before implementation. Use during $wio scan, $wio workload, or the discovery stage of $wio test.

workersio/skills

Agent

Part of wio

Read-only WIO subagent for challenging the selected testing strategy before implementation. Use after candidate selection and before editing test files.

workersio/skills

Agent

Part of wio

Read-only WIO subagent for reviewing a written test and deciding KEEP, REDO, or REMOVE. Use after $wio test edits a test, or when asked whether a test is valuable.