Skill Claude CodeCodex
Security audit checklist based on OWASP Top 10 and best practices. Covers authentication, injection, XSS, CSRF, secrets management, and more. Use when reviewing security, before deploy, asking "is this secure", "security check", "vulnerability".
Skill Claude CodeCodex
Generate professional Agent Skills for AI agents. Creates complete skill packages with SKILL.md, references, scripts, and templates. Use when creating new skills, generating custom slash commands, or building reusable AI capabilities. Validates against Agent Skills specification.
Skill Claude CodeCodex
Verify completed implementation against the plan. Checks that all tasks were fully implemented, nothing was forgotten, code compiles, tests pass, and quality standards are met. Use after "$aif-implement" completes, or when user says "verify", "check work", "did we miss anything".
Skill Claude CodeCodex
Set up agent context for a project. Analyzes tech stack, installs relevant skills from skills.sh, generates custom skills, and configures MCP servers. Use when starting new project, setting up AI context, or asking "set up project", "configure AI", "what skills do I need".
Agent Claude Code
Read-only background best-practices sidecar for the current implementation scope. Use from implement-coordinator after code changes when a concise maintainability review is needed.
Agent Claude Code
Read-only background commit preparation sidecar for the current implementation scope. Use from implement-coordinator when deciding whether a final /aif-commit step can be streamlined.
Agent Claude Code
Read-only background documentation drift sidecar for the current implementation scope. Use from implement-coordinator after code changes when deciding whether /aif-docs should run automatically.
Agent Claude Code
Coordinate parallel execution of independent plan tasks. For single tasks — implements directly with quality sidecars. For parallel tasks — dispatches implement-worker workers. Use via claude --agent implement-coordinator.
Agent Claude Code
Execute a single plan task in an isolated worktree — implement, verify, and return. Spawned by implement-coordinator for parallel task execution. Cannot spawn child agents — runs quality checks locally.
Agent Claude Code
Convert failed evaluation rules into precise, minimal fix instructions for the refiner. Use proactively within /aif-loop when evaluation fails.
Agent Claude Code
Evaluate artifact strictly against active loop criteria and return structured pass/fail output. Use proactively within /aif-loop when an objective verdict is needed.
Agent Claude Code
Prepare invariant and consistency checks for the current loop iteration. Use proactively within /aif-loop in parallel with producer.
Agent Claude Code
Route reflex-loop execution to the next role based on run state, stop guards, and last evaluation. Use proactively within /aif-loop when deciding the next step.
Agent Claude Code
Prepare lightweight performance checks (RPS/latency budget assertions) for the current loop iteration. Use proactively within /aif-loop in parallel with producer.
Agent Claude Code
Build a short, execution-focused iteration plan (3-5 steps) aligned to active rules. Use proactively within /aif-loop when the next iteration plan is needed.
Agent Claude Code
Produce the single markdown artifact for the current loop iteration from task and plan. Use proactively within /aif-loop when artifact generation is needed.
Agent Claude Code
Apply critique issues to produce a minimally changed improved artifact. Use proactively within /aif-loop when refinement is needed after failed evaluation.
Agent Claude Code
Prepare lightweight test checks for the current loop iteration without blocking execution. Use proactively within /aif-loop in parallel with producer.
Agent Claude Code
Iteratively polish a plan by launching plan-polisher in a loop until critique passes or max iterations reached. Use via claude --agent plan-coordinator.
Agent Claude Code
Create or refresh an /aif-plan plan, critique it, and run one refinement round at most. The caller launches another plan-polisher for further iterations if needed.
Agent Claude Code
Read-only background code review sidecar for the current implementation scope. Use from implement-coordinator after code changes when a concise bug-risk review is needed.
Agent Claude Code
Read-only background rules compliance sidecar for the current implementation scope. Use from implement-coordinator after code changes when a concise rules check is needed.
Agent Claude Code
Read-only background security audit sidecar for the current implementation scope. Use from implement-coordinator after code changes when a concise security check is needed.
Command Claude Code
On-demand adversarial implementation review. Invoke when POST-REVIEW needs a deeper look or after COMMIT when something feels off.