Skip to content

My5t3r10us/cesizen / .agents/skills/apex

Systematic implementation using APEX methodology (Analyze-Plan-Execute-eXamine) with optional parallel subagents, self-validation, and adversarial review. Use when implementing features, fixing bugs, or making code changes that benefit from structured workflow.

<quick_start>

/apex add authentication middleware           # Basic
/apex -a -s implement user registration       # Autonomous + save
/apex -a -x -s fix login bug                  # With adversarial review
/apex -a -v implement user dashboard          # With feature verification
/apex -a -m implement full auth system        # Parallel subagents
/apex -a -x -s -t -v add auth middleware      # Full workflow with tests + verify
/apex -a -pr add auth middleware              # With PR creation
/apex -r 01-auth-middleware                   # Resume previous task
/apex -e add auth middleware                  # Economy mode (save tokens)
/apex -i add auth middleware                  # Interactive flag config

</quick_start>

ONOFFLongDescription
-a-A--autoSkip confirmations, auto-approve
-x-X--examineAdversarial code review
-s-S--saveSave outputs to .claude/output/apex/
-t-T--testInclude test creation + runner
-v-V--verifyLaunch app and verify feature works
-e-E--economyNo subagents, save tokens
-b-B--branchVerify not on main, create branch
-pr-PR--pull-requestCreate PR at end (enables -b)
-i--interactiveConfigure flags via menu
-k-K--tasksTask breakdown with dependencies
-m-M--teamsParallel subagent execution (enables -k)
-r--resumeResume from previous task ID

Parsing: Defaults from steps/step-00-init.md, flags override, remainder = {task_description}, ID = NN-kebab-case.

<step_files>

StepFilePurpose
00steps/step-00-init.mdParse flags, initialize state
00bsteps/step-00b-save.mdSetup save output structure (if -s)
00bsteps/step-00b-branch.mdGit branch setup (if -b)
00bsteps/step-00b-economy.mdEconomy mode overrides (if -e)
00bsteps/step-00b-interactive.mdInteractive flag config (if -i)
01steps/step-01-analyze.mdSmart context gathering
02steps/step-02-plan.mdFile-by-file plan + TaskList
02bsteps/step-02b-tasks.mdTask breakdown (if -k/-m)
03steps/step-03-execute.mdTodo-driven implementation
03tsteps/step-03-execute-teams.mdAgent Team execution (if -m)
04steps/step-04-validate.mdSelf-check and validation
05steps/step-05-examine.mdAdversarial code review
06steps/step-06-resolve.mdFinding resolution
07steps/step-07-tests.mdTest analysis and creation
08steps/step-08-run-tests.mdTest runner loop
09steps/step-09-finish.mdCreate pull request
10steps/step-10-verify.mdLaunch & verify feature

</step_files>

<state_variables>

VariableTypeSet by
{task_description}stringstep-00
{feature_name}stringstep-00
{task_id}stringstep-00 / step-00b-save
{acceptance_criteria}liststep-01
{auto_mode}booleanstep-00
{examine_mode}booleanstep-00
{save_mode}booleanstep-00
{test_mode}booleanstep-00
{verify_mode}booleanstep-00
{economy_mode}booleanstep-00
{branch_mode}booleanstep-00
{pr_mode}booleanstep-00
{tasks_mode}booleanstep-00
{teams_mode}booleanstep-00
{output_dir}stringstep-00b-save
{branch_name}stringstep-00b-branch

</state_variables>

<execution_rules>

  • Load one step at a time (progressive loading)
  • ULTRA THINK before major decisions
  • Persist state variables across all steps
  • Follow next_step directive at end of each step
  • Save outputs if {save_mode} = true (each step appends to its file)
  • Use parallel agents for independent exploration (step-01) </execution_rules>

<entry_point> FIRST ACTION: Load steps/step-00-init.md </entry_point>

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall