code-critic
AgentReviews code changes against project standards after implementation is complete. MUST be invoked before presenting any work to…
@cunhaaxInstall AgentDevelopment
Agent
adversarial-qa
Runs an exploratory, adversarial pass over a feature after the code-critic passes, through whichever surface(s) it exposes (UI via Playwright, API via curl/Bash). Probes beyond the plan and committed tests for issues and edge cases they did not anticipate; does not re-verify the
Claude Code
> /plugin marketplace add cunhaax/ai-workflow> /plugin install ai-workflow@ai-workflow
Cursor
Cursor also loads subagents from .claude/agents, so copy this file there to use it in Cursor.
Agent definition
adversarial-qa.mdname: adversarial-qa
description: "Runs an exploratory, adversarial pass over a feature after the code-critic passes, through whichever surface(s) it exposes (UI via Playwright, API via curl/Bash). Probes beyond the plan and committed tests for issues and edge cases they did not anticipate; does not re-verify the spec or review code style.\n"
tools: Read, Bash, mcp__plugin_ai-workflow_playwright__browser_click, mcp__plugin_ai-workflow_playwright__browser_close, mcp__plugin_ai-workflow_playwright__browser_console_messages, mcp__plugin_ai-workflow_playwright__browser_drag, mcp__plugin_ai-workflow_playwright__browser_evaluate, mcp__plugin_ai-workflow_playwright__browser_file_upload, mcp__plugin_ai-workflow_playwright__browser_fill_form, mcp__plugin_ai-workflow_playwright__browser_handle_dialog, mcp__plugin_ai-workflow_playwright__browser_hover, mcp__plugin_ai-workflow_playwright__browser_navigate, mcp__plugin_ai-workflow_playwright__browser_navigate_back, mcp__plugin_ai-workflow_playwright__browser_network_requests, mcp__plugin_ai-workflow_playwright__browser_press_key, mcp__plugin_ai-workflow_playwright__browser_resize, mcp__plugin_ai-workflow_playwright__browser_run_code_unsafe, mcp__plugin_ai-workflow_playwright__browser_select_option, mcp__plugin_ai-workflow_playwright__browser_snapshot, mcp__plugin_ai-workflow_playwright__browser_tabs, mcp__plugin_ai-workflow_playwright__browser_take_screenshot, mcp__plugin_ai-workflow_playwright__browser_type, mcp__plugin_ai-workflow_playwright__browser_wait_for, mcp__plugin_ai-workflow_playwright__browser_network_request, mcp__plugin_ai-workflow_playwright__browser_find, mcp__plugin_ai-workflow_playwright__browser_emulate_media
model: sonnet
effort: medium
skills:
- adversarial-qa
Adversarial QA
Apply the `/adversarial-qa` skill to the feature you are given.
Read more
name: adversarial-qa description: "Runs an exploratory, adversarial pass over a feature after the code-critic passes, through whichever surface(s) it exposes (UI via Playwright, API via curl/Bash). Probes beyond the plan and committed tests for issues and edge cases they did not anticipate; does not re-verify the spec or review code style.\n" tools: Read, Bash, mcp__plugin_ai-workflow_playwright__browser_click, mcp__plugin_ai-workflow_playwright__browser_close, mcp__plugin_ai-workflow_playwright__browser_console_messages, mcp__plugin_ai-workflow_playwright__browser_drag, mcp__plugin_ai-workflow_playwright__browser_evaluate, mcp__plugin_ai-workflow_playwright__browser_file_upload, mcp__plugin_ai-workflow_playwright__browser_fill_form, mcp__plugin_ai-workflow_playwright__browser_handle_dialog, mcp__plugin_ai-workflow_playwright__browser_hover, mcp__plugin_ai-workflow_playwright__browser_navigate, mcp__plugin_ai-workflow_playwright__browser_navigate_back, mcp__plugin_ai-workflow_playwright__browser_network_requests, mcp__plugin_ai-workflow_playwright__browser_press_key, mcp__plugin_ai-workflow_playwright__browser_resize, mcp__plugin_ai-workflow_playwright__browser_run_code_unsafe, mcp__plugin_ai-workflow_playwright__browser_select_option, mcp__plugin_ai-workflow_playwright__browser_snapshot, mcp__plugin_ai-workflow_playwright__browser_tabs, mcp__plugin_ai-workflow_playwright__browser_take_screenshot, mcp__plugin_ai-workflow_playwright__browser_type, mcp__plugin_ai-workflow_playwright__browser_wait_for, mcp__plugin_ai-workflow_playwright__browser_network_request, mcp__plugin_ai-workflow_playwright__browser_find, mcp__plugin_ai-workflow_playwright__browser_emulate_media model: sonnet effort: medium skills: - adversarial-qa
Adversarial QA
Apply the `/adversarial-qa` skill to the feature you are given.
Stats
5
Stars
0
Forks
Active
Maintenance
Shell
Language
MIT
License
Last commit
Created
Ships withai-workflow
Turns Claude Code into a small development team instead of one agent guessing alone — with a git-level gate that keeps the humans in charge of what actually ships.
59 skills4 agents2 MCP
Stars on GitHub
Momentum
- stars in total
- 5
Other agents on ai-workflow.
@cunhaaxInstall Agentplan-critic
AgentCritiques a draft implementation plan using pre-mortem, inversion, load-bearing assumption analysis, and consistency checks…
@cunhaaxInstall AgentMore agents from other plugins.
Auto-invoked
cavecrew-builder
AgentSurgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard…
@juliusbrusseeInstall AgentQuestions about adversarial-qa.
- Which coding agents can use adversarial-qa?
- adversarial-qa installs in Claude Code and Cursor: each loads subagents from .claude/agents, so copy the file there. Flowy's auto-invocation runs in Claude Code only.