
Capture a project fact and route it to the correct context document -- production map, dangerous assumptions, decision log, institutional knowledge, or troubleshooting
Design discussion before decomposition — produce a ~200-line design artifact for human review, catching wrong assumptions before they propagate into specs
Brainstorm freely about what you want to build — yap, explore ideas, and get a structured summary you can use later
Generate constrained execution boundaries for an implementation session -- NEVER rules and deny patterns to prevent agent overreach
Wrap up a session — capture discoveries, verify, prepare for PR or next session
Execute atomic specs with TDD — read spec, write failing tests, implement until green, hand off to session-end
Produce objective codebase research by isolating question generation from fact-gathering — subagent sees only questions, never the brief
Assess and upgrade your project's AI development harness — score 7 dimensions, apply fixes, show path to Level 5
Break a feature brief into atomic specs — small, testable, independently executable units
Capture a project fact and route it to the correct context document -- production map, dangerous assumptions, decision log, institutional knowledge, or troubleshooting
Structured bug fix workflow — triage, diagnose, discuss with user, write a focused spec, hand off for implementation
Structured bug fix workflow — triage, diagnose, discuss with user, write a focused spec, hand off for implementation
Set up Level 5 autonomous development — autofix loop, holdout scenario testing, and scenario evolution from specs
Guided feature development — interview the user, produce a Feature Brief, then decompose into atomic specs
Guided feature development — interview the user, produce a Feature Brief, then decompose into atomic specs
Audit your Claude Code or Codex session overhead — harness file sizes, plugins, MCP servers, hooks — and report actionable recommendations
Produce objective codebase research by isolating question generation from fact-gathering — subagent sees only questions, never the brief
Spawn an independent verifier subagent to check an implementation against its spec -- read-only, no code edits, structured pass/fail verdict
Spawn an independent verifier subagent to check an implementation against its spec -- read-only, no code edits, structured pass/fail verdict
Break a feature brief into atomic specs — small, testable, independently executable units
Set up Level 5 autonomous development — autofix loop, holdout scenario testing, and scenario evolution from specs
Execute atomic specs with TDD — read spec, write failing tests, implement until green, hand off to session-end
Audit your Claude Code or Codex session overhead — harness file sizes, plugins, MCP servers, hooks — and report actionable recommendations
Assess and upgrade your project's AI development harness — score 7 dimensions, apply fixes, show path to Level 5
Design discussion before decomposition — produce a ~200-line design artifact for human review, catching wrong assumptions before they propagate into specs
Brainstorm freely about what you want to build — yap, explore ideas, and get a structured summary you can use later
Generate constrained execution boundaries for an implementation session -- NEVER rules and deny patterns to prevent agent overreach
Wrap up a session — capture discoveries, verify, prepare for PR or next session