Agent Claude Code
Use this subagent before any non-trivial implementation work. The architect produces specs (docs/specs/ .md), implementation plans (docs/specs/ .plan.md), and Architecture Decision Records (docs/decisions/NNNN- .md). Use proactively when the user asks to "build", "design", "plan", "architect", or describes a new…
Agent Claude Code
You are the Delivery Orchestrator. You coordinate the autonomous delivery pipeline; you are not a builder, reviewer, release engineer, or merge bot.
Agent Claude Code
Write external-facing DevRel content — Twitter/X threads, LinkedIn posts, YouTube video scripts, podcast outlines, conference talk abstracts, hackathon submission narratives, customer-facing announcements. Use this subagent when the user asks to "draft a thread", "write a script for the video", "outline the talk"…
Agent Claude Code
Execute an approved implementation plan task by task using strict TDD. Use this subagent when there's an approved spec at docs/specs/ .md and plan at docs/specs/ .plan.md and the operator says "implement" / "execute the plan" / "build it". Refuses to start without an approved plan.
Agent Claude Code
Independently review code changes for bugs, security issues, performance problems, edge cases, and Definition of Done coverage. Read-only — no write tools. Use this subagent after the implementer completes a plan, before opening any PR, after receiving Copilot review comments, or whenever the user asks "review this"…
Agent Claude Code
Specialized security review subagent invoked automatically when changes touch authentication, cryptography, money flows, medical data (PHI), or network-exposed surfaces (RPC, gRPC, public APIs). Also use when the user asks "security review", "is this safe", "OWASP check", "audit this for vulnerabilities", or before…
Agent Claude Code
Write or rewrite technical documentation, READMEs, changelogs, blog posts (technical), API references, runbooks, and architecture docs. Use this subagent when the user asks to "document this", "write a README", "draft a blog post about X", "write release notes", "explain this technically", or whenever the deliverable…
Command Claude Code
Run the daily supply-chain audit on demand (also runs automatically every morning).
Command Claude Code
Drive a governed idea-to-PR Walter-OS delivery cycle with feature-state, planning, TDD, review, and human gates.
Command Claude Code
Ingest a source (URL, file path, or pasted text) into the operator's LLM-maintained wiki at $WALTEROSHOME/wiki/. Reads the source, drafts a sources/ - .md page, identifies referenced entities (people / companies / tools / concepts), creates stub pages with [[wikilinks]], updates topic hubs, and appends to log.md.…
Command Claude Code
Prepare and (in personal/ context) open a PR after the implementer is done. In work/ ([Company]), prepares everything but stops short of opening the PR.
Command Claude Code
Inspect or restart Walter-OS time-bounded session state.
Skill Claude CodeCodex
Autonomous researcher agent in the Walter Council. Picks up Plane issues with lane:research label, ingests the linked source(s) into the operator's wiki at $WALTEROSHOME/wiki/ via the wiki-ingest skill, and reports back with the list of pages created/updated. Triggered by walter-os agents run-once researcher --issue…
Skill Claude CodeCodex
Track LLM API spend across Anthropic, OpenAI, and Google providers, project daily and monthly cost, alert when burn rate exceeds threshold, and circuit-break agent loops before they cost serious money. Use this skill when starting a long agentic session, when the user asks "how much have I spent on AI", "what's my…
Skill Claude CodeCodex
Walter-VM lightweight alerting — replaces PagerDuty / Opsgenie complexity with a 4-tier stack pushing to a single Telegram bot. Use this skill whenever the user asks "set up alerts", "I want to know if a service goes down", "monitor my LLM spend", "Hetzner cost alert", or anything related to monitoring +…
Skill Claude CodeCodex
Create a complete brand identity for a project — name, logo, color palette, typography, and voice/tone — using nanobanana for visual generation. Use this skill when starting a new project ([Project A], [Project B], hackathons), when the user asks to "create a brand", "design a logo", "make an identity", "moodboard for…
Skill Claude CodeCodex
Draft a personalized 5-touch cold outreach sequence for email, LinkedIn, or Twitter/X DM. Each touch includes personalization variables, subject line A/B options, and reply-trigger templates. Triggers on: cold outreach, email sequence, LinkedIn outreach, DM sequence, founder outreach.
Skill Claude CodeCodex
Track competitor moves across changelog, pricing, hiring, and blog. Three phases: Setup (define competitors.yml), Snapshot (fetch and diff current state), Synthesis (emit weekly change report). Uses WebFetch only, no external dependencies. Triggers on: competitor radar, track competitors, competitor changes, what…
Skill Claude CodeCodex
Pre-audit prep checklists for GDPR compliance, SOC2 prep, PCI-DSS checklist, ISO 27001, and HIPAA. Five-question applicability gate per framework. Outputs self-assessment checklist with evidence templates, gap analysis, and remediation priorities. Not legal advice.
Skill Claude CodeCodex
Brand-voice-aware content writer. Five modes: blog post (800-2000 words, TL;DR + CTA), Twitter thread (8-15 tweets, hook-driven), YouTube script (intro hook + 3-act + outro CTA), newsletter issue (300-700 words), press release (AP-style). Reads assets/brand/ /voice.md when present. Triggers on: blog post, twitter…
Skill Claude CodeCodex
Two-phase customer discovery tool. Phase A: generate a Mom Test-compliant interview script from a hypothesis and target persona. Phase B: synthesize 1-N interview transcripts into pain points, JTBD, recurring quotes, and recommended pivots. Triggers on: interview script, customer discovery, synthesize interviews, jobs…
Skill Claude CodeCodex
Run a comprehensive daily security audit of all installed MCP servers, Claude Code skills, agent configs, and AI CLI tooling. Detects supply chain attacks, tool-name shadowing, malicious skills, configuration drift, missing CVE patches, and untrusted package versions. Use this skill EVERY MORNING before starting work…
Skill Claude CodeCodex
Review database migrations and schema changes for safety — reversibility, lock duration, online-vs-offline behavior, batch-size on backfills, tenant isolation, RLS policies (Supabase), idempotence, audit-log impact. Use this skill on any PR that touches migrations/, supabase/migrations/, .sql, schema files…
Skill Claude CodeCodex
Capture significant decisions in a structured format — decision journal, log this decision, important decision, decision review. Stores entries at /.config/walter-os/state/decisions/. Surfaces past-due revisit prompts via weekly-review-coach.
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: