heyAyushh

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

Design, critique, set, create, activate, or run durable Codex goals for persistent or long-running objectives. Use when the user says "set a goal", "start a goal", "activate goal mode", "persistent goal", "long-running objective", "goal tree", or asks for a goal with verifiers, durable state, approval gates, completion proof, bounded delegation, or parent/child subagent goals.

Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors, idempotency, dry-run, and predictable structure. Use when building a CLI, adding commands, writing --help, or when the user mentions agents, terminals, or automation-friendly CLIs.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Expert Bash help for writing, debugging, and optimizing safe, portable shell one-liners and scripts on macOS/Linux. Use when users ask for Bash or POSIX sh commands, script reviews, ShellCheck fixes, quoting/pipeline issues, process/file automation, or converting requirements into shell scripts.

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

Secrets manager workflow for OpenClaw operators and agents. Use when you need the safe OpenClaw plugin tools, redacted metadata checks, request review flows, or the private Docker shim examples for `/run/secrets/...` delivery.

Expert Bash help for writing, debugging, and optimizing safe, portable shell one-liners and scripts on macOS/Linux. Use when users ask for Bash or POSIX sh commands, script reviews, ShellCheck fixes, quoting/pipeline issues, process/file automation, or converting requirements into shell scripts.

Identifies and fixes common Rust anti-patterns. Use during code review, when seeing excessive clones/unwraps/index loops, or when code fights the borrow checker instead of working with it.

50 core Rust coding conventions covering naming, data types, strings, error handling, memory, concurrency, async, and modern crate recommendations. Use when reviewing code style or setting up project conventions.

Guides concurrency and async decisions in Rust. Use when encountering Send/Sync errors (E0277), choosing between threads vs async, designing shared state, or debugging deadlocks.

Guides Rust error handling strategy. Use when choosing between Result/Option/panic, using anyhow vs thiserror, propagating errors with ?, or designing custom error types.

Guides ownership, borrowing, and lifetime decisions in Rust. Use when encountering E0382, E0597, E0506, E0507, move errors, or when designing data ownership.

Guides Rust performance optimization. Use when profiling, benchmarking, reducing allocations, improving cache locality, choosing between rayon/async/threads, or applying SIMD/parallelism.

Build, maintain, and operate the contract-driven hook workspace with serve/relay/smash roles, Kafka core transport, and plug-and-play adapters. Use when editing runtime behavior, contract validation, adapter/plugin execution, or deployment documentation.

Maintain the kafka-openclaw-hook compatibility binary and its integration with hook-runtime smash execution. Use when changing startup wiring, runtime env expectations, deployment compatibility, or smash adapter/plugin behavior.

Maintain shared relay-core contracts, validation, envelope models, and security primitives used by serve, relay, smash, and hook-runtime. Use when changing contract schema, active-profile validation, model compatibility, or signature/sanitization/timestamp logic.

Add a new webhook source to hook serve. Covers implementing the SourceHandler trait, registering the handler, adding HMAC secret config, creating the Kafka topic, and writing tests. Use when integrating a new webhook provider (e.g. Stripe, PagerDuty, Bitbucket).

Provision and operate Apache Kafka in KRaft mode inside a Firecracker microVM without Docker, including host networking, guest bootstrap, systemd service, and security checks. Use when setting up a lightweight isolated Kafka broker for internal pipelines such as hook serve/relay/smash Kafka core transport.

Trace a webhook through the full hook pipeline (serve → relay → smash), inspect Kafka topic contents, check consumer group lag, and replay messages from the DLQ. Use when a webhook is lost, delayed, or failing delivery, or when diagnosing any serve/relay/smash runtime issue.

End-to-end release process for hook: version bumps, local validation gate, binary release via tag push, and crates.io publish in dependency order. Use when cutting a new release or diagnosing a failed publish.

Write, validate, and debug hook contract.toml files. Covers the full schema (app, policies, serve, smash, profiles, transports), all supported driver config keys, validation rules, plugin system, and common error codes. Use when creating a new app contract, extending an existing one, or diagnosing contract validation failures.

Install and configure the Seagrass language server for the user's editor. Use when the user says "install seagrass", "set up seagrass", "configure seagrass in vscode/zed/vim/helix/neovim", "get seagrass running", or "wire seagrass into my project". Walks through source or release binary install, per-editor configuration, and a smoke check that real diagnostics fire on a Solana program.

Add a Seagrass diagnostic suppression at the narrowest correct scope. Use when the user says "suppress this seagrass warning", "ignore this finding", "silence seagrass for this line/file/project", "add seagrass-allow", or "this is a false positive, suppress it". Picks the right suppression form (line, item/block, file, workspace, or Cargo project switch) and writes the comment or config.

Explain a Seagrass diagnostic topic — what it catches, what it doesn't, false-positive matrix, and suppression syntax. Use when the user says "what does this seagrass topic mean", "explain seagrass/<...>", "why is seagrass flagging this", "what's the topic for unsafe unwrap", or pastes a Seagrass error message. Pulls authoritative content from `docs/lints/<topic>.md`.

Run Seagrass diagnostics on a Solana program file or workspace and surface findings ranked by severity and topic. Use when the user says "lint my program", "run seagrass", "check my anchor code", "show seagrass issues", "find security problems", or "what's wrong with this account struct". Parses JSON output, groups by topic, and recommends suppression vs fix per finding.

Investigate a Seagrass false positive — confirm it's actually false, identify the rule and region that misfired, and produce a minimal regression fixture for upstream. Use when the user says "seagrass is wrong here", "this is a false positive", "why is seagrass flagging valid code", "debug this seagrass diagnostic", or "file a seagrass bug". Outputs a reproducible fixture and a draft upstream issue body.

Run a full Seagrass quality audit on a Solana project — diagnostics by severity and topic, suppression review, and an actionable summary. Use when the user says "audit my program", "full seagrass check", "is my anchor code clean", "review for production", "production readiness check", or "what does seagrass say about all of this". Produces a triaged report and a punch list.

Inspect Trust Substrate snapshots and, when explicitly enabled, preview or submit Solana protocol writes with the bundled MCP server. Use when Codex needs receipt history, agent profiles, task handoffs, domain activity, or controlled Trust Substrate transaction tools.

Derive and implement first-principles audio-coupled haptic and kinetic UI feedback. Use when designing, reviewing, or coding haptics/audio for mobile apps, native iOS/Android, React Native/Expo, SwiftUI, games, detent pickers, toggles, sliders, page curls, scroll gestures, wallet/signature flows, Solana transactions, backend/realtime state changes, confirmations, settlements, and semantic UI events where feedback should follow signal math instead of ad hoc vibration calls.