The Dark Factory method — autonomous, governed, evidence-gated delivery.
Skill Claude CodeCodex
Review architectural changes for coupling, blast radius, and long-term impact. Use when evaluating system design changes, cross-service dependencies, API changes, or infrastructure modifications. Triggers on "architecture review", "impact analysis", "blast radius", "coupling review", "dependency analysis", "breaking…
Skill Claude CodeCodex
Audit backend services for security, reliability, performance, and operability issues. Use when reviewing APIs, microservices, workers, or backend code changes. Triggers on "audit backend", "security review", "service audit", "API audit", "check vulnerabilities", "review microservice", "backend security", "audit API"…
Skill Claude CodeCodex
Comprehensive code review for quality, architecture, and performance. Use when reviewing PRs, auditing code quality, checking coding standards, evaluating design patterns, identifying performance bottlenecks, or analyzing technical debt. Triggers on "review", "audit", "analyze code", "check quality", "code smell".
Skill Claude CodeCodex
Analyzes any microservice codebase and generates a complete cold-start package — CLAUDE.md, custom skills, requirements template, development process docs, and onboarding guide. Works for any architecture. Use when setting up AI-assisted development for a new project. Triggers on "cold start", "set up AI development"…
Skill Claude Code
Create high-quality Claude Code skills with proper structure, effective descriptions, and best practices. Use when creating a new skill, writing SKILL.md files, setting up skill directories, or asking how to make skills.
Skill Claude CodeCodex
Proactively challenge implementation plans, architecture decisions, and design assumptions. Use when reviewing plans, designs, or technical decisions. Verifies claims via web search, cross-references documentation, identifies risks and gaps, and surfaces hidden assumptions. Activates automatically when evaluating…
Skill Claude Code
End-to-end Dark Factory build orchestrator: intent to shipped software via the df- stages, test-first, adversarially verified, autonomous in dev/non-prod, documented as stage docs plus tickets. Triggers on "build this the dark factory way", "run a dark factory build", "take this spec to done end-to-end".
Skill Claude CodeCodex
Analyze third-party dependencies for security, maintenance, and lock-in risk. Use when auditing dependencies, reviewing new packages, or assessing supply chain security. Triggers on "dependency audit", "package risk", "supply chain", "vulnerable dependencies", "license check", "outdated packages", "dependency review"…
Skill Claude CodeCodex
Run the adversary gate: assess whether presented evidence proves a promise was kept, without redoing the work and never trusting a self-report. Use before trusting any "done/passing" claim, PR, or handoff. Triggers on "adversary review", "verify", "gate", "assess evidence", "is this really done".
Skill Claude Code
Dark Factory Stage 0.5 — scaffold a repo's in-repo agent inner-loop substrate (read-first context store + single-responsibility agents + checkable hand-off contracts + commit gate) from the proven template, populate it from the real codebase, and verify it. Use when bootstrapping a repo for DF work, running a DF…
Skill Claude Code
Navigate the codebase cheaply by reading the context store first, not re-scanning the repo. Use at the start of any investigation, feature, or review to locate the relevant service/file fast and with minimal tokens. Triggers on "where is", "how does X work", "understand the code", "find the service for".
Skill Claude Code
Commit workflow — before committing, sync the knowledge layer (context store, per-service CLAUDE.md, and the agents/skills routing README) to the change, then draft a proper commit message and push. Use for "commit", "commit and push", "ship this", "save my work". Always stops for explicit approval before pushing.
Skill Claude Code
Maintain and compress the context store so analysis is done once and reused, never repeated. Use to record a confirmed root cause, an architecture decision, or a service/contract change; or to compress sprawling notes back into the terse store. Triggers on "remember this", "update the context", "record decision", "we…
Skill Claude Code
Trace a request/data flow end-to-end across services, queues, databases, object stores, and APIs to find every component a change or bug touches. Use when a problem spans boundaries or before changing a shared contract. Triggers on "trace the flow", "what depends on", "blast radius", "end to end path", "who…
Skill Claude Code
Design a minimal-impact implementation for a new feature or fix before any code is written — files to touch, contracts, migrations, risks, and a test plan. Use for "implement X", "add feature", "how should we build this". Reuses the context store; records the decision as an ADR.
Skill Claude Code
Turn a symptom into a confirmed root cause using evidence, not guesses — across any service, DB, queue, API, or infra. Use for "find the bug", "why is this failing", "0 records / stuck / DLQ / timeout / wrong data". Checks known findings first; escalates when evidence is missing instead of assuming.
Skill Claude Code
Decide what to test and write the tests for a change — regression guards, edge cases, cross-service contracts — and scaffold the test project in the repo's conventions. Use after a fix or feature, or to assess coverage. Triggers on "write tests", "test coverage", "regression test", "validate change", "review test…
Skill Claude CodeCodex
Model any system as data nodes (schema, origin, authority) and transforms tagged pure|effect, governed by validation rules and an authority that resolves conflicts. The shared frame the other df- skills build on. Triggers on "data contract", "data flow", "validation rule", "transform", "pure or effect", "authority"…
Skill Claude CodeCodex
Dispatch sub-agents under Promise Theory: state the promise plus the exact unforgeable evidence required, withhold holdout cases, verify the evidence not the self-report. USE EVERY TIME you spawn a sub-agent. Triggers on "dispatch sub-agent", "spawn agent", "parallel agents", "delegate", "fan out".
Skill Claude CodeCodex
Dark Factory Infrastructure stage: produce the Deployment and Infrastructure Spec — DTAP placement, where data lives, trust boundaries mapped to enforcement mechanisms, secrets, and a verified observability surface. Triggers on "infrastructure", "deployment", "trust boundary", "where data lives", "deploy across…
Skill Claude CodeCodex
Dark Factory Observability stage: make the consumable surface (dashboards and queryable traces keyed to scenarios, verified rendering live data) a named deliverable — a /metrics endpoint nobody can see is not observability. Triggers on "observability", "dashboards", "Grafana", "correlationId trace", "telemetry…
Skill Claude CodeCodex
Dark Factory Product Owner stage: define Vision, Requirements as data contracts plus validation rules, and Test Scenarios — the semantics every later stage derives from. Triggers on "product owner", "requirements", "acceptance criteria", "test scenarios", "data contract", "what should we build".
Skill Claude CodeCodex
Run the Dark Factory QA stage — execute the validation rules as tests, capture unforgeable evidence per scenario (by correlationId), run the holdout, and return a Works? verdict. QA is the OBSERVER: a self-report is not an assessment. Use when testing a deployed system, mapping PO scenarios to test cases, verifying…
Skill Claude CodeCodex
Dark Factory Solution Architect stage: turn PO semantics into a Data Model, Data Flow (transform graph, pure|effect, idempotency, compensation) and Service Map, assigning each validation rule an enforcement locus. Triggers on "architecture", "data model", "data flow", "service map", "schema", "Avro contract"…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: