- adversarial-plan-approvalbyayagmar
Independently falsify or approve implementation plans before execution with ACCEPT, MODIFY, or REJECT verdicts per task…
- hyper-questionsbyemo-eth
Interactive question runner for Pi and OMP with incremental state saving, pause/resume, and backtracking.
- pi-casefilebyxaccefy
Offensive security case ledger for Pi Agent — evidence tracking with machine-verified PoC gates.
- advisor-executor-quality-loopbyayagmar
Orchestrate complex multi-task work by separating advisor reasoning, delegated execution, and independent verification…
- engineering-optimizationbyayagmar
Improve performance, resource use, determinism, or simplicity through measurement, profiling, benchmarks, and proven…
- implementation-plan-authorbyayagmar
Author self-contained implementation plans, multi-plan programs, or compact handoffs that a fresh agent can execute…
- product-spec-foundrybyayagmar
Turn a product idea, loose PRD, or inconsistent pre-implementation repository into an implementation-ready…
- release-readiness-certificationbyayagmar
Produce a strict evidence-based release verdict with severity-ranked findings, blockers, a pre-release work batch, and…
- session-cost-forensicsbyayagmar
Analyze local Codex, Pi, and Claude Code session logs for cost, token waste, cache misses, retries, and duplicate…
- session-memory-searchbyayagmar
Search local Codex, Pi, and Claude Code session history to recover prior decisions, feedback, prompts, and conversation…
- x-post-craftbyayagmar
Write and review X/Twitter posts and threads using the reach mechanics of X's open-source recommendation stack.