The library

finish-l4-lora-recipe · Orchestrating multi-agent workflows with bounded costs and structured outputs.

synthetic-round-trip · Orchestrating multi-agent workflows with bounded costs and structured outputs.

security-audit · Conducting structured code/design reviews with multiple perspectives in parallel.

wf-swarm-synthesize · Gathering diverse perspectives and synthesizing a single authoritative result.

software-factory-pipeline · When coordinating feature development with model-selection, telemetry, and integrated deployment.

vjs-supreme-court · When resolving constitutional questions requiring multi-justice written opinions and case law synthesis.

audit · When finding latent defects across mixed languages with mechanical refutation of false positives.

vcs-eval-start-round · When measuring whether agents properly isolate before editing a shared repository.

build-shell-v2 · When layering open-source packages with typed contracts that must stay green at each step.

mishkan-knowledge-gap-discovery · When auditing whether expected knowledge exists or needs research to fill gaps.

loop-until-budget · When a task needs to run repetitively until completion or token budget exhaustion.

full-quality-gate · When integrating code and docs require automated compliance gates before promotion.

test · When running tests needs detailed instrumentation and result aggregation.

kiln-validate · When validating codegen artifacts must match strict schema conformance rules.

evo-optimize · When iteratively refining codegen output requires evolutionary feedback loops.

fan-out.template · When executing parallel agents on the same arguments without manual orchestration.

env-ctl-audit-phase1 · When auditing infrastructure configuration state against policy in parallel.

adversarial-verify · When testing correctness claims requires independent skeptics voting on evidence.

software-dev-pipeline · When driving full software development with design, implementation, verification, and deployment.

jira-digest · When generating team digests from Jira activity with structured, parseable output.

mishkan-codebase-audit · Periodic project-wide audits, pre-release reviews, post-incident hardening passes.

opsx-verify · Run after apply to prove each spec requirement is satisfied.

parallel-review · Use when workflow operations need parallel review.

comprehensive-review-workflow · Use when workflow operations need comprehensive review workflow.

compass-plan · Before a non-trivial or ambiguous change where the approach is not obvious.

design · Use when workflow operations need design.

worktree-isolation · Use when workflow operations need worktree isolation.

finish-l2-transformer-block · Continuing the toy-framework P2 refactor after L1: extract the L2 TransformerBlock as a single gated unit.

{PROJECT_NAME}-autoresearch · Use when workflow operations need {PROJECT_NAME} autoresearch.

long-chain-diagnostics-audit · Use when workflow operations need long chain diagnostics audit.

cr-multi · Use when workflow operations need cr multi.

tools-vs-effecttools · Use when workflow operations need tools vs effecttools.

wfl:run-task · Run a single Forge task through its full plan→implement→review→approve→commit pipeline via a deterministic JS driver instead of the LLM orchestrator.

oagp-seat-doc-reviewer · Use when workflow operations need oagp seat doc reviewer.

fathomdb-0.8.0-slice-plan · Planning large multi-phase database implementations with complex dependency sequencing and human-in-loop gates.

finish-l4-warmstart-curriculum · Building deterministic multi-stage training recipes with bit-identical gating vs. reference curves.

comms-workflow · Continuous monitoring and triage of PR comments with automated fixes and intelligent re-request logic.

panim-ds-rollout · Propagating design token changes across component consumers with a11y and visual regression gates.

sefer-release-notes · Assembling release notes from commits when different categories need orthogonal specialist perspectives.

playwright-parallel-test · Running parallel UI tests across form/nav/layout when isolation and concurrent feedback matter.

codeclash-decomp-evolution · Evolving multi-agent harnesses via selection pressure with verified fitness gates and ablation analysis.

mine-claude-md-from-sessions · Extracting and synthesizing codebase documentation from session transcripts.

loom-orchestrate · Coordinating loom weaving with pattern composition and constraint satisfaction.

wc-generate · Generating contextual content via word-chain models and sampling.

context-refresh · Refreshing and updating cached context for downstream tasks.

jc-axiom-discharge-plans · Generating clinical discharge plans using axiom-driven logic.

chosheb-feature-ship · Shipping features with automated checklists and verification gates.

architecture-docs · Generating architecture documentation from code analysis and design specs.

qa-tenancy · Running tenancy-aware QA tests across isolated environments.

p1-wave-light · Sequence complex CAD modeling tasks with phase gates and registry reconciliation.