joelhooks

Develop, deploy, and debug the system-bus worker — joelclaw's 110+ Inngest durable function engine, webhook gateway, and observability pipeline. Triggers on 'add a function', 'new inngest function', 'system-bus', 'worker', 'add a webhook', 'deploy worker',…

Verify, repair, backfill, and back up Pi/Claude/Codex session capture across active machines. Use when checking whether agent activity is captured, reviewing capture outbox backlogs, backing transcripts up to NAS, or scheduling capture verification.

iMessage/SMS CLI for listing chats, reading message history, watching for new messages, and sending messages. Triggers on: check messages, read imessage, send text, imsg, message history, sms, who texted me.

Ingest PDF/Markdown/TXT files into joelclaw's docs memory pipeline with Inngest durability, durable NAS artifacts, and OTEL verification. Use when adding docs, running batch reindex, reconciling coverage, or recovering stuck runs. Triggers on: 'ingest pdf',…

Research and library synthesis from the docs/PDF corpus, mapped to joelclaw system philosophy and concrete operational actions (especially k8s reliability). Trigger on: 'research this', 'from the library', 'from the books', 'pdf brain', 'correlate this',…

Operate the joelclaw gateway daemon — the always-on pi session that receives events, notifications, and messages. Use the joelclaw CLI for ALL gateway operations. Use when: 'restart gateway', 'gateway status', 'is gateway healthy', 'push to gateway', 'gateway…

Create new joelclaw skills with the idiomatic process — repo-canonical, symlinked, git-tracked, slogged. Triggers on 'add a skill', 'create skill', 'new skill', 'canonical skill', 'make a skill for', or any request to formalize a process or domain into a…

Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before…

Send messages, system events, and agent notifications through the openclaw CLI. Use when an agent needs to notify a user (Telegram, Slack, Discord), trigger another agent, broadcast updates, send system events, or coordinate agent-to-agent communication via…

Handles version bumps and npm releases for the swarm-tools monorepo (opencode-swarm-plugin, claude-code-swarm-plugin, swarm-mail, swarm-queue). Use when: creating changesets, bumping versions, preparing releases, checking release status, debugging publish…

Always-on rule-oriented guidance for claude-plugin agents. Use to align behavior, tool usage, and model-specific defaults while avoiding deprecated bd/cass references. Related skills: swarm-coordination, testing-patterns.

Multi-agent coordination patterns for OpenCode swarm workflows. Use when work benefits from parallelization or coordination. Covers: decomposition, worker spawning, file reservations, progress tracking, and review loops.

Always-on rule-oriented guidance for claude-plugin agents. Use to align behavior, tool usage, and model-specific defaults while avoiding deprecated bd/cass references. Related skills: swarm-coordination, testing-patterns.

Ralph loop pattern - Claude supervises while Codex (gpt-5.3-codex) executes implementation work. Use for autonomous coding loops with fresh context per iteration, validation gates, and git-backed persistence. Tools: ralph_init, ralph_story, ralph_iterate,…

Swarm CLI commands for workers - hivemind memory, hive tasks, swarmmail coordination. Use when working in a swarm context. Covers: swarm memory (find/store/get/stats), swarm cells (query/create/update/close), and coordination commands.

Multi-agent coordination patterns for OpenCode swarm workflows. Use when work benefits from parallelization or coordination. Covers: decomposition, worker spawning, file reservations, progress tracking, and review loops.

Trace a capability through Effect, XState, five projections, the CLI, and Alchemy. Try hosted search and read.

Learn how XState owns a lifecycle while Effect owns its work, errors, and services.

Keep rat-stack current and clean. Update exact dependency versions, learn from repos on the same versions, and add lint rules before cleanup.

Find responsibilities that a rat-stack design combines, separate them into capabilities, cartridges, machines, features, and clients, and enforce that separation through types and checks. Use when asked to simplify, review, or replace a design, "what would…

Learn how to ship a change through merge, CI, release, stage deployment, rollout, verification, rollback and flags.

Design or review SQL reads, writes, scans, backfills, and slow database paths. Use before changing a store method or any loop that queries. Covers round-trip arithmetic, batching, keyset paging, index evidence, row budgets, PlanetScale Vitess limits,…

Learn how Alchemy 2 turns an Effect program into a planned Cloudflare deployment.

Route non-trivial rat-stack code, data, design, investigation, and documentation tasks to every matching playbook and principle.

Build and maintain the native iOS client inside this turborepo (XcodeGen, SwiftUI, WebSocket feed). Use when creating/updating the iOS app, wiring turbo tasks, or documenting iOS workflows.

Publish the native iOS app to TestFlight from this repo. Use when archiving/exporting/uploading builds, bumping versions, checking App Store Connect processing status, or fixing common upload failures.

Deploy the atproto-agent-network project. Two separate Cloudflare Workers must be deployed independently — the network worker (API + agents) and the dashboard worker (highswarm.com). Use when deploying changes, fixing the dashboard, or updating agent configs.

Cloudflare Durable Objects patterns for agent state. Use when implementing agent DOs, WebSocket handling, hibernation, storage API, alarms, or DO-to-DO communication. Triggers on Durable Object, DO state, WebSocket server, hibernation, agent persistence.

Pi agent runtime integration for Cloudflare. Use when implementing the agent loop, tools, extensions, session trees, or multi-provider LLM calls. Triggers on Pi, agent runtime, tool calling, streaming, session tree, extensions, self-extending agent.

D1 database patterns for encrypted agent records. Use when implementing schema, storing/querying encrypted records, migrations, or working with the records table. Triggers on D1, database, schema, records table, SQL, encrypted storage.

Envelope encryption patterns with X25519 for agent memories. Use when implementing key generation, DEK management, encrypting/decrypting records, key rotation, or sharing encrypted data between agents. Triggers on encryption, X25519, DEK, envelope encryption,…

Vectorize semantic search patterns for agent memory. Use when implementing embedding generation, semantic search, memory retrieval, or working with the Vectorize API. Triggers on Vectorize, embeddings, semantic search, vector database, similarity search.

Extend alchemy-celld with a resource a real consumer needs. Use when adding resource types, provider lifecycle methods, schemas, outputs, or public exports.

Decide what earns a place in alchemy-celld. Use when proposing a resource, option, dependency, test, export, or cleanup, or when extracting consumer-specific code.

Keep slice limit changes from becoming disruptive restarts. Use when changing systemd limits, reviewing replacement plans, or modifying unit reconciliation. The enforced scope is active slice updates, not a global plan veto.

Keep data purge explicit. Use when changing delete behavior, storage ownership, adoption, purge options, or destroy plans.

Prove systemd behavior on a real user manager. Use when changing lifecycle, activation waiting, slice limits, restart safety, or claiming that a deployment works.

Separate this provider's responsibilities. Use when simplifying, reviewing architecture, adding a resource or option, or deciding where behavior belongs. Parent skill for the enforced principles.

Declare celld and its object store in a consumer Alchemy stack. Use when installing the provider, wiring host inventory or providers, composing resources, or reviewing a consumer plan.

Keep mutation single-attempt and retries around readback only. Use when adding retries, SSH operations, deployment calls, bucket mutations, or failure recovery.

Learn how XState owns a lifecycle while Effect owns its work, errors, and services.

Keep rat-stack current and clean. Update exact dependency versions, learn from repos on the same versions, and add lint rules before cleanup.

Learn how Alchemy 2 turns an Effect program into a planned Cloudflare deployment.

Trace a capability through Effect, XState, five projections, the CLI, and Alchemy. Try hosted search and read.

Route non-trivial rat-stack code, data, design, investigation, and documentation tasks to every matching playbook and principle.

Learn how to ship a change through merge, CI, release, stage deployment, rollout, verification, rollback and flags.

Find responsibilities that a rat-stack design combines, separate them into capabilities, cartridges, machines, features, and clients, and enforce that separation through types and checks. Use when asked to simplify, review, or replace a design, "what would…

Write or revise public wiki pages with short prose, cited claims, meaningful visuals, and pinned code snippets.

Learn how one contract and its handler become a command, HTTP route, MCP tool, browser RPC, and sandbox call.

Learn how XState owns a lifecycle while Effect owns its work, errors, and services.

Keep Calendar current and clean. Update exact dependency versions and add lint rules before cleanup.

Learn which pieces depend on each other, then keep only the ones your project needs.

Route non-trivial rat-stack code, data, design, investigation, and documentation tasks to every matching playbook and principle.

Learn how to ship a change through merge, CI, release, stage deployment, rollout, verification, rollback and flags.

Search and verify Joel's Pi, Claude, Codex, Cursor, Grok, and OpenCode session history. Use when asked to recover prior context, find exact transcript evidence, inspect session receipts, continue old work, or verify capture health. Prefer flowing recall…

Historical pointer for the retired Codex-to-Central capture plugin. Use only to inspect legacy state during migration; current capture belongs to the joelclaw flowing-memory host adapter.

Create joel.dev shortlinks and QR assets. Use when Joel asks for a QR code, stage/demo shortlink, joel.dev redirect, link label that looks good in phone camera UI, or a copyable QR asset.

Resolve project-local issue tracker routing and publish Linear issues safely. Use before creating Linear issues, PRDs, phase breakdown issues, or when deciding whether Linear/GitHub/local docs is the configured tracker. Enforces capability ≠ routing: Linear…

Create distinctive, crafted TUI components for pi using @mariozechner/pi-tui and @mariozechner/pi-coding-agent. Use when building interactive terminal UIs — custom components, overlays, dialogs, dashboards, widgets, data visualizations, animated elements,…

Design or review crash recovery, retries, duplicate delivery, overload, worker ownership, replay, and durable timers in Effect applications. Use when work can outlive a request, a worker loses progress, retries repeat writes, or a queue grows under failure.

Pressure-test a stateful system or replacement design through Rich Hickey's simplicity and complection, Greg Young's deletability, Ousterhout's deep modules, DDD boundaries, typed effects, explicit lifecycle modeling, and Lauren Tan's agent-sized context. Use…

Keep rat-stack current and clean. Update exact dependency versions, learn from repos on the same versions, and add lint rules before cleanup.

Route non-trivial rat-stack code, data, design, investigation, and documentation tasks to every matching playbook and principle.

Post GitHub issue comments, inline PR review replies, PR reviews, edit pull requests, small file commits, annotated tags, and releases as the ShitRat GitHub App (`shitratgit[bot]`) instead of Joel. Use when reviewing PRs, replying to review threads, updating…

Draft and publish X.com Articles and inspect X OAuth2 user identity through the ShitRat CLI. Use when posting an X Article, converting HTML or markdown to X DraftJS content_state, uploading an article cover, publishing a draft, or when an agent reaches for…

Front inbox janitor for Joel's personal shitbox: Brain-mapped executive digests, contextual grouping, safe archive sweeps, and Front thread links. Use when asked to clean the shitbox, summarize inbox, run a digest, sweep personal Front, or tune inbox interest…

Maintain, install, update, doctor, and release a ShitRat familiar across supported harnesses.

Transform raw Programming/Movement Source Sheet rows into Rubicon's programming write operations (create_node, patch_node, create_edge, patch_edge), applying conjugate-method coaching conventions and resolving movement IDs via movement_catalog_search. Use…

Run a dry run of a Rubicon programming write batch via programming_write_dry_run to get a confirmationToken and a human-readable preview of the change before anything is published. Use this as stage 3 of the Rubicon programming pipeline, after…

Publish a previewed Rubicon programming write batch via programming_write_publish using the confirmationToken from the preview step. Use this as stage 4 (final) of the Rubicon programming pipeline, after the coach has explicitly approved the preview.

Read rows from the coach's Programming Source Sheet and/or Movement Source Sheet using gogcli, resolving the real spreadsheet ID from local plugin data instead of any hardcoded value. Use this as stage 1 of the Rubicon programming pipeline, before…

Local teaching assistant for a Loopcraft learner workspace. Use when building the connected issue-progress loop, shaping the local issue checker control surface, choosing the next step, setting up pnpm/TypeScript/tsgo/oxlint/oxfmt/Ultracite and Git/Lefthook…

Delegate work to builtin or custom subagents with single-agent, chain, parallel, async, forked-context, and intercom-coordinated workflows. Use for advisory review, implementation handoffs, and multi-step tasks where a single agent should stay in control…

Interview the plan one sharp question at a time, inspect local docs before asking, and save clear decisions back into the right repo docs.