Quality

Hivemind Code Graph queries a local AST-derived code graph to answer structural questions about a codebase. Use it to find definitions, callers, imports, architectural layers, and change impact before reading the actual source.

Hivemind Graph queries a local AST-derived code graph (functions, classes, calls, imports) through a Deeplake mount. Use it for structural questions like "what calls X?", "where is Z defined?", or to trace dependency paths and impact before changing a signature.

Implements UVM-based hardware verification testbenches including stimulus generation, scoreboarding, coverage-driven verification, and assertion-based testing.

Adversarial Squad deploys a bounded, profile-loaded review squad at SDD point-cuts so independent doctrine lenses converge on findings one reviewer would miss. Use it after spec, plan, tasks, or before merge for a multi-lens review or brownfield check.

Spec Kitty Bulk Edit recognizes bulk-edit missions and applies occurrence classification guardrails before modifying many matching instances. Use it for broad renames, replacements, migrations, or classifications where the blast radius spans multiple occurrences.

Spec Kitty Mission Review audits a fully merged Spec Kitty mission after all work packages are done and approved, verifying that merged code accurately and completely realizes the spec and surfacing drift, risks, and security issues. Use it before tagging a release or signing off on spec-to-code fidelity.

Spec Kitty Runtime Review loads review context, claims work packages, reads generated review prompts, and issues approval or rejection with structured feedback. Use it when reviewing runtime-owned outputs in the Spec Kitty workflow.

Audit Reproducibility compares numeric claims in a manuscript against actual analysis outputs and reports PASS/FAIL per claim against tolerance thresholds. Use it before submission, before releasing a replication package, or after a major revision to catch mismatches between the paper and the code.

Deep Audit launches four parallel specialist agents to find factual errors, code bugs, count mismatches, and cross-document inconsistencies across a repository, then fixes all issues and loops until clean. Use it after broad changes, before releases, or when asked to audit or check everything.

Devil's Advocate critically examines a slide deck and challenges its design with 5-7 specific pedagogical questions. Use it when you want to stress-test slides, poke holes in a deck, or hear what a skeptical student might ask.

Diagnose root-causes a failing or wrong empirical result with a disciplined reproduce → minimise → hypothesise → instrument → fix loop, instead of guessing-and-poking. Use when a regression is wrong, a number changed, a script errors, a result won't reproduce, or an estimate looks wrong.

Disclosure Check scans analysis outputs built on restricted or confidential data for statistical disclosure limitation problems before any release. Use it before exporting from a secure enclave or sharing results derived from confidential microdata.