Plugin Claude Code
Bundles 3 skills · 559 tokens together
Persistent, per-objective working memory for coding agents — one standalone git notepad per objective that survives compaction, spans multiple code repos from a single session, keeps an append-only journal, and mirrors into an episodic memory index. Evolves and supersedes handoff-auto.
Settings file Claude Code
Agent settings declaring 1 hook event (PreToolUse).
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 Code needs its repo
Upload or download large files to/from a Coder CDE workspace using the coder CLI. Use when transferring files, directories, build artifacts, datasets, or binaries to a Coder workspace, when rsync -e "coder ssh" fails or desyncs, or when a copy over coder ssh hangs/corrupts. Triggers on "upload to coder", "copy files…
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…
Agent Claude Code
Feature Architect. Designs the minimal-impact implementation for a new feature or a confirmed fix — files to touch, contracts, migrations, risks, test plan — without writing code. Consumes a requirement (or a Root Cause) and the context store; produces a Design Spec for the implementer. Use for "how should we build…
Agent Claude Code
Code Implementer. Writes the actual code changes for a Design Spec — only after requirements are clear. Implements per the design, keeps the diff minimal, and updates contracts/migrations consistently. Use for "implement this", "make the change", once a plan/Design Spec exists. Does not invent scope.
Agent Claude Code
System Investigator (read-only). Traces a flow across ANY service, DB, queue, API, or infra component and gathers the evidence around a symptom or change area. Does NOT decide the root cause and does NOT edit code — it produces a structured Evidence Bundle for the root-cause-analyzer or feature-architect. Use first…
Agent Claude Code
Knowledge Keeper. Maintains the context store (SERVICE-MAP, FINDINGS, DECISIONS) and per-service CLAUDE.md so analysis is done once and reused — preventing repeated investigation and keeping token use low. Records confirmed root causes and decisions; compresses; fixes stale docs against source. Use for "remember…
Agent Claude Code
Root Cause Analyzer. Consumes an Evidence Bundle (from the investigator) and determines the actual root cause and mechanism — without re-scanning the whole repo. Returns a structured Root Cause with fix options (no code). Use for "explain the root cause", "why does this happen", after evidence is gathered.
Agent Claude Code
Validation Agent (adversarial verifier). Verifies a change does what it should — derives its OWN edge cases/holdout, exercises them, checks regressions and cross-service contract breaks. Consumes a change (diff/Design Spec) as UNTRUSTED input and returns a Validation Report with a clear verdict + unforgeable evidence.…
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 needs its repo
Validate an agent hand-off (Evidence Bundle, Root Cause, Design Spec, Implementation Report, Validation Report, Knowledge Entry) against its data contract before consuming it. Use at any pipeline seam to enforce LOCAL-reject ("escalate, don't guess") and the unforgeable-evidence rule (a PASS must carry test counts)…
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…
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: