The library

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.

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

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

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

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.

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

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.

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

build-harness · Running build-harness as a multi-phase orchestrated workflow.

vcs-eval-round · Running vcs-eval-round as a multi-phase orchestrated workflow.

nvptx-author-tests · Running nvptx-author-tests as a multi-phase orchestrated workflow.

skill-audit-detect · Running skill-audit-detect as a multi-phase orchestrated workflow.

snake-script-bestofn-r2 · Optimize a small game or component for minified size when multiple implementation strategies compete.

bb-skill-bodies · Document a security skill when reference materials exist and a consistent body structure is needed.

mishmar-security-gate · Gate a sensitive merge when orthogonal security expertise and adversarial refutation are required.

sdlc-refactor-by-module · Refactor multiple modules in parallel when each has an isolated scope and a test suite.

skill-audit-remediate · Apply bulk skill remediation when decisions span multiple files and lane isolation is guaranteed.

fuzz-kql-translator · Find bugs in a KQL-to-SQL translator when seeded fuzzing families and differential testing are available.

root-cause · Diagnose a failure when multiple evidence sources exist and hypothesis generation needs to avoid anchoring.

repo_review · Review a code change for bugs and design issues when structured findings and effort levels matter.

sganit-production-hardening · Harden a production system when systematic audit and controlled rollout are required.

mishkan-release-readiness · Gate a release when multi-layer verification and structured blocker tracking are required.

code-review-deep · Review code when multi-lens analysis (correctness + design) and configurable effort are required.

bench-s4-parallel-2stage · Measuring wall-clock cost of serialization barriers vs pipelined concurrency

compass-review · High-confidence PR review when 5 concurrent reviewers + skeptic-per-finding beats single-pass

review-changes · Quick lightweight review when changes are small + reasoning-only suffices

nvptx-author-fixes · Compiler bug fixing when root cause is documented + one-off minimal edits suffice (not redesigns)

sdlc-review-team · Deterministic multi-role PR review when you want procedural routing but human retains merge gate

metal-trait-bridge-removal · Rust-specific refactoring when manual trait bridge removal is tedious + well-scoped

gc-review-fidelity · QA pass after section build when pixel-perfect fidelity is required

verify-council · Verification when author needs raw multi-lane input + bears adjudication burden themselves

migdal-infra-change · Non-trivial infrastructure changes (network, IAM, scaling) where blast-radius analysis spans design, systems, devops, observability, and health.

fanout · Batched parallel work where cost/quota capping is required and partial-failure detection is needed.

todo-scanner · Quick inventory of technical debt across a Python codebase when distributed priorities and actionable top-3 recommendations are needed.

systems-check-workflow · Iterative code review when language-specific inspectors and optional specialist agents (security, perf, migration) are needed and findings must be actionable.

bug-hunt · Exploratory correctness/security/resource-leak testing when multiple independent finders and majority-refute skeptics must verify candidates.

kokimoto-migration · Version upgrades of complex config systems when automated transformation and validation must preserve backward compatibility.

claude-md-audit-detect · Multi-repo governance when CLAUDE.md documentation standards must be enforced and drift detected.