The library

kiln-report · Executing the kiln-report workflow.

dead-code-scan · Use when you need a structured dead code scan workflow.

wf-grill · Use when you need a structured wf grill workflow.

writer-reviewer · Use when you need a structured writer reviewer workflow.

opsx-propose-deep · Use when you need a structured opsx propose deep workflow.

agent-daily-digest · Use when you need a structured agent daily digest workflow.

implement-and-review · Use when you need a structured implement and review workflow.

dashboard · Use when you need a structured dashboard workflow.

adversarial-verify · Use when you need a structured adversarial verify workflow.

dependency-audit · Use when you need a structured dependency audit workflow.

autoresearch-loop · Use when you need a structured autoresearch loop workflow.

df-ula-file-pass · Use when you need a structured df ula file pass workflow.

path-warden-review-fix · Use when you need a structured path warden review fix workflow.

why-investigate · Use when you need a structured why investigate workflow.

writing-review · Use when you need a structured writing review workflow.

multica-layout-review · Use when you need a structured multica layout review workflow.

l3-phase · Use when you need a structured l3 phase workflow.

fih-review · Use when you need a structured fih review workflow.

pathlib-refactor · Use when you need a structured pathlib refactor workflow.

research · Use when you need a structured research workflow.

ci-fixer · Use when you need a structured ci fixer workflow.

dashclaw-preship-sweep · Running go/no-go pre-deployment checks in parallel with cost-optimized model routing (cheap + expensive gates).

verify-phase35 · Composing advisory testing targets conditionally based on change scope, feeding into deterministic ship/hold verdicts.

snake-script-bestofn-r1 · Minimizing compiled Svelte component size while maintaining correctness across diverse implementation strategies.

validate-translations · Fleet-reviewing translations at scale with consistent criteria and rework categorization.

glossary-extract · Extracting domain terminology from curated pairs while normalizing and deduplicating.

repo-qa-and-doc-correctness · Auditing a repo across multiple dimensions (frontend, CI, scripts, docs) and applying doc corrections.

cadence-report · Self-compiling LaTeX sections with visual verification and fixing before assembly.

evolve-understand · Mapping current state of a codebase across multiple facets before design decisions.

sdlc-brownfield-inventory · Inventorying legacy repos across standardized dimensions without claiming maturity.

nvptx-find-miscompiles · Hunting for LLVM backend miscompiles through multi-agent code-reading.

verify-cs · Composing advisory testing targets conditionally based on change scope, feeding into deterministic ship/hold verdicts.

evloop-adversarial-break · Adversarial stress-testing through evolution and mutation loops.

layer1-classify · Initial categorical bucketing of items before detailed processing.

gimle-ab-sweep · Running A/B experiments with parallel variant evaluation and statistical reporting.

mishkan-sprint-close · Closing sprints with task completion audit and next-phase handoff.

driver-catalog-first-g1 · First-pass cataloging of driver entities with schema conformance.

playlist-subs-batch · Batch subscription management with parallel confirmation and state sync.

ccgp-paper · Synthesizing research papers from sourced content with citations.

qa-weekly · Running standardized QA weekly with regression detection and reporting.

layer2-extract · Deep extraction and classification after layer-1 initial bucketing.

lets-review · Getting high-confidence review feedback when multiple reviewers agreeing matters more than speed.

hunt-workflow · Systematic multi-angle bug hunting where cross-cutting defects need skeptic verification.

sdlc-qa-sweep · Verifying mandatory invariant acceptance criteria in parallel when hard gates matter.

sharp-review · Merging feedback from 3+ reviewers with dedup when you want convergent high-confidence findings.

docaudit-impact-verify · Checking whether docs still match source after changes without re-reading entire files.

adversarial-verify · Testing if a claim stands up to multiple independent refutation attempts.

loop-until-dry · Exhausting paginated or incremental sources without manual pagination logic.

wf-swarm-explore · Exploring large task spaces where pheromone-guided parallel paths find good solutions.

review-loop · Applying fixes in a loop until an independent verifier signs off on final diff.