The library
Everything we index — ranked by what works, never by stars.
forSalesMarketingHRFinanceLegalOpsProductEngineeringDataProductivitySupportsetup≤ plug & play≤ + a key≤ multi-tool
WORKS 56★0WORKS 54★0WORKS 54★0WORKS 54★0WORKS 54★0WORKS 54★0WORKS 54★0WORKS 54★0WORKS 54★0WORKS 54★0WORKS 57★0WORKS 57★0WORKS 54★0WORKS 54★0WORKS 59★0WORKS 53★0WORKS 59★0WORKS 58★0WORKS 55★0WORKS 59★0WORKS 55★0WORKS 59★0WORKS 60★3WORKS 55★0WORKS 56★5WORKS 55★0WORKS 55★4WORKS 54★4WORKS 55★2WORKS 60★3WORKS 58★0WORKS 55★0WORKS 55★0WORKS 55★0WORKS 55★0WORKS 53★0WORKS 55★0WORKS 58★0WORKS 54★0WORKS 58★0WORKS 56★0WORKS 55★0WORKS 57★0WORKS 55★0WORKS 57★2WORKS 58★3WORKS 60★0WORKS 55★0WORKS 58★0WORKS 54★0
Process CI failures with 2-vote reviewworkflowEngineeringL3
phase-h-ci-tasks · Coordinating multi-agent workflows with explicit phases, budget guards, and structured JSON output schemas.
Complete product polish checklistworkflowProductL3
sessionvault-product-polish · Coordinating multi-agent workflows with explicit phases, budget guards, and structured JSON output schemas.
Port unimplemented stubs to ZigworkflowEngineeringL4
phase-e-body-port · Transitive porting of stub implementations with 2-vote verification per file.
Audit codebase idioms and anti-patternsworkflowEngineeringL3
phase-h-idioms-audit · Cataloging anti-patterns across a codebase in a single pass with enforced coverage.
Hunt and fix Windows-specific bugsworkflowEngineeringL3
phase-h-windows-bughunt · Detecting platform-specific bugs (HANDLE leaks, UTF-16 bounds, error code mapping) statically.
Fix failing tests with root cause analysisworkflowEngineeringL3
phase-g-test-swarm · Massively parallel test crash categorization across shards without reimplement runners.
Survey and batch-fix build errors by subtreeworkflowEngineeringL3
phase-d-subtree-batch · Staged multi-agent compilation loops with spec-grounded verification.
Resolve cargo build errors iterativelyworkflowEngineeringL3
phase-d-build-queue · Staged multi-agent compilation loops with spec-grounded verification.
Audit unsafe pointer and cast patternsworkflowEngineeringL3
phase-d-unsafe-audit · Exposing raw-pointer aliasing bugs that rust-clippy misses and require semantic analysis.
Apply refactors with 2-vote reviewworkflowEngineeringL3
phase-f-reviewed-refactor · Staged multi-agent compilation loops with spec-grounded verification.
Adversarially review and fix code plansworkflowEngineeringL3
review-and-fix-plan · Staged multi-agent compilation loops with spec-grounded verification.
Test isolated code shards with resourcesworkflowEngineeringL3
phase-g-test-swarm-isolated · Massively parallel test crash categorization across shards without reimplement runners.
Verify ported code matches mainworkflowEngineeringL3
phase-h-main-parity · Staged multi-agent compilation loops with spec-grounded verification.
Fix Windows test failures in parallelworkflowEngineeringL3
phase-h-windows-testfix · Detecting platform-specific bugs (HANDLE leaks, UTF-16 bounds, error code mapping) statically.
Audit libuv integration for memory bugsworkflowEngineeringL3
phase-h-libuv-audit · Verifying uv_* handle lifecycle rules and double-free detection without integration tests.
Find unnecessary Zig idioms in portworkflowEngineeringL2
porting-md-zigleakage · Staged multi-agent compilation loops with spec-grounded verification.
Build functional vault with encryptionworkflowEngineeringL3
env-ctl-phase1b-vault · Staged multi-agent compilation loops with spec-grounded verification.
Conduct deep research with citationsworkflowL2
deep-research · Adversarial deep research with multi-source verification and ranked evidence synthesis.
Plan object model migration strategyworkflowEngineeringProductL3
generic-harness-object-model-research · Adversarial deep research with multi-source verification and ranked evidence synthesis.
Implement Meridian modules in parallelworkflowEngineeringL3
meridian-impl · Staged multi-agent compilation loops with spec-grounded verification.
Manage tools workflowworkflowL2
tools · Staged multi-agent compilation loops with spec-grounded verification.
Execute workflow taskworkflowL2
short_snake_case · Staged multi-agent compilation loops with spec-grounded verification.
Fix documentation and code driftworkflowEngineeringL3
doc-drift-fix · Iterative multi-phase workflows with safeguards.
Resolve all parity findingsworkflowEngineeringL3
parity-fix · Iterative multi-phase workflows with safeguards.
Audit entire codebase for bugsworkflowEngineeringL3
compass-audit · A deep audit of an area or the whole repo — more coverage than one review pass. Scope it with args.path (e.g.
Evaluate sprint contract dynamicallyworkflowEngineeringProductL3
harness-eval · Iterative multi-phase workflows with safeguards.
Audit dependencies for securityworkflowEngineeringOpsL3
dependency-audit · Monthly per repo, before major releases, or when adding a significant new dependency. Surface critical security findings
Compare AI models dailyworkflowDataProductL3
model-arena-daily · Daily intelligence on which Claude tier is best for each task type. Cost-disciplined by design: 3 generators + 1 judge =
Verified swarm executionworkflowL2
verified-swarm.workflow · Catching error-suppression in automated fixes via voting.
Decompose issue into sub-issuesworkflowEngineeringProductL2
decompose-issue · When a task is too large for one ticket and should become a parent + several sub-issues on phaabe/live.moafunk.de
Review code diff for conventionsworkflowEngineeringL3
review-diff · Catching error-suppression in automated fixes via voting.
Prepare dispatch scaffoldingworkflowEngineeringProductL2
dispatch-prep · When Leader wants to dispatch the Developer subagent manually in main chat but still benefit from the preflight + scaffo
Sweep for untested business logicworkflowEngineeringFinanceL3
coverage-sweep · Iterative multi-phase workflows with safeguards.
Verify commit claims before pushworkflowEngineeringL2
pre-push-verify · Before git push of a feature branch, before gh pr create, before gh pr merge. Especially after rebase / amend / worktree
Draft feature flags in parallelworkflowEngineeringL3
ws-bf-fanout · Catching error-suppression in automated fixes via voting.
Discover targets through iterative deduplicationworkflowSalesMarketingL3
loop-discover · When the amount of work is unknown upfront — bugs, proposals, patterns. Spawns finder agents until K consecutive rounds
Generate verified science curriculum questionsworkflowProductEngineeringL3
author-content · Generating science curriculum MCQ items with guaranteed content accuracy and grade-fit validation through adversarial verification.
Batch-process design chapter rewritesworkflowProductL3
author-rework-batch · Iterative multi-phase workflows with safeguards.
Audit AI game engine capability gapsworkflowEngineeringL3
p6-complete-dm-gap-audit · Iterative multi-phase workflows with safeguards.
Polish workflow visualization mapsworkflowEngineeringL3
polish-ascii-map · Iterative multi-phase workflows with safeguards.
Improve workflow GUI usabilityworkflowProductEngineeringL3
polish-gui · Iterative multi-phase workflows with safeguards.
Multi-agent Go code review pipelineworkflowEngineeringL3
verify-go-review · Catching error-suppression in automated fixes via voting.
Parallelize sprint story implementationworkflowEngineeringL3
harness-implement-group · Iterative multi-phase workflows with safeguards.
Diagnose agent evaluation failuresworkflowEngineeringL3
wave-analysis · Root-cause analysis across multi-scenario runs with dedup and regression detection.
Run security scans across OWASP Top 10workflowEngineeringLegalL3
forge-check-security · OWASP parallel scanning (6 dimensions) with risk aggregation and gate enforcement.
Audit research findings for completenessworkflowDataL3
grounding-audit · Parallel read-only audits against design claims with completeness criticism.
Fix and test path traversal vulnerabilityworkflowEngineeringL3
fix-harvest-security · OWASP parallel scanning (6 dimensions) with risk aggregation and gate enforcement.
Generate daily research briefworkflowDataMarketingL3
research-pulse-daily · Daily lightweight research pulse: 3 parallel domain scans + synthesis.
Harden committer resource injectionworkflowEngineeringL3
fix-committer-harvest · Security hardening: fixer → test-writer → adversarial reviewer loop.
Implement feature with review loopworkflowEngineeringL2
implement-and-review · Iterative code review → fix loops up to 3 rounds, hard-capped.