hushh-research

Use when changing One Voice capability authoring, Kai compatibility runtime contracts, generated action gateway contracts, typed-search and voice parity, persona/workspace gating, or BYOK-safe durable voice memory.

Use when reviewing an incoming pull request for north-star alignment, trust-boundary regressions, malicious or low-signal degradation, stale-vs-current CI interpretation, and true merge readiness beyond a green gate. Also owns PR train planning, merge queue cohorts, maintainer patch-then-merge, contributor harvest decisions, and backlog review waves.

Use when operating reviewer-account browser rehearsals that require BYOK unlock, memory-only decrypted information, and same-session client navigation.

Use when changing Hussh UI architecture, shared components, shell chrome, or styling rules inside the frontend owner family.

Use when drafting or polishing founder-facing architecture briefs, presentation-grade markdown/html/pdf artifacts, generic report PDFs, Drive/shareable artifacts, or paper-style technical specs that must stay grounded in repo truth.

Use when inspecting, summarizing, creating, triaging, or updating work on the Hussh Engineering Core GitHub board.

Use when changing Morphy AX shared agent-experience state, semantic assessment presentation, performance budgets, or cross-modal compatibility.

Use when changing Hussh frontend structure, route contracts, package-level conventions, or frontend verification ownership.

Use when working on Hussh CI/CD, branch protection, merge queue, GitHub Actions, deploys, env or secret parity, Cloud Run or Cloud Build operations, UAT or production rollout, incident triage, or operational verification.

Use when choosing, running, or verifying scoped UAT deploys for Hussh Cloud Run services, including frontend-only/backend-only scope, Cloud Build timing proof, Cloud Run region discovery, and service provenance evidence.

Use when proving zero-loss PKM upgrades with historical fixtures, reviewer rehearsals, rollback, scopes, and exact encrypted/decrypted artifacts.

Running reference log of every iOS/mobile bug diagnosed + fixed on the `mobile` branch (symptom → root cause → fix → files/commit), plus the recurring build/runtime gotchas that keep biting. Use when the user asks "what bugs did we fix", "known issues", "list the resolved bugs", "why did X break", when a similar symptom reappears (check if it's a known regression before re-diagnosing), or before shipping a mobile build (re-verify the gotchas). ALWAYS append a new entry here whenever another mobile bug is resolved.

Use when an OpenClaw agent needs to access a Hussh One user's Personal Knowledge Model through the Hussh MCP bridge. This covers developer-token setup, dynamic scope discovery, explicit user consent in One/Kai, consent polling, scoped export retrieval, and the privacy boundary for external agents.

Use when creating, renaming, retrofitting, linting, or scaffolding repo-local Codex skills for hushh-research.

Use when a request starts with scanning the Hussh repository, establishing repo context, mapping code/docs/skills, or deciding which owner skill should own the next step.

Use when the request is broadly about IAM, consent, trust, vault, PKM, streaming safety, verification, or audit workflows and the correct security specialist skill is not yet clear.

Use when changing vault boundaries, PKM storage rules, encrypted information handling, or ordinary vault/PKM persistence behavior inside the security-audit owner family.

Use when changing Apache-2.0 licensing, SPDX/REUSE coverage, package license metadata, or third-party notice generation across consent-protocol and hushh-research.

Use when changing optional-mirror coordination, subtree sync policy, or maintainer-only subtree governance between consent-protocol and hushh-research.

Use when operating the Hussh Consent MCP core lifecycle or campaign compatibility tool for scope search, consent checks, or scoped export verification.

Use when the request is broadly about the Hussh web frontend and the correct frontend specialist skill is not yet clear.

Use when reorganizing docs, deciding documentation homes, consolidating redundant docs, updating diagrams or doc maps, or changing documentation verification policy in this repo.

Use when changing repo-scoped Codex custom agents, subagent concurrency or depth, delegation policy, or handoff verification rules in hushh-research.

Use when changing backend route placement, service boundaries, runtime ownership, or backend docs/tests alignment.

Use when changing IAM, consent scopes, actor model, verification policy, or marketplace access contracts inside the security-audit owner family.

Use when changing cross-surface verification policy, contract-test placement, test selection, or quality gates across frontend and backend.

Use when changing backend agents, operons, ADK surfaces, or orchestration contracts inside the consent-protocol runtime.

Use when the request is broadly about backend runtime, API routes, services, agents, or protocol package behavior and the correct backend specialist skill is not yet clear.

Build the hushh One webapp, sync it into the native iOS shell, and launch it on the iPhone 16 simulator (UDID B46FD09B-E0BC-400E-821B-5CE3D575ECAB) against the UAT backend. Use when the user asks to run/launch/build the app on the simulator, take a screenshot on device, or verify a change in the real native app. Wraps the mobile build gotchas (UAT backend override, Node 22, 8 GB heap, /tmp DerivedData) into one command.

Use when changing SSE events, streaming payload contracts, parser behavior, degraded-state handling, or provider-specific streaming notes.

Use when auditing or changing Hussh frontend cache-first screen behavior, warm-cache UX, stale-while-revalidate resources, route TTL policy, or reviewer-backed cache coherence checks.

Use when changing or auditing the generated mapping between app routes, page files, Next.js API proxies, backend endpoint families, native transport, Capacitor plugins, and voice/action contracts.

Use when auditing mobile/native parity, release readiness, or platform-specific coverage across the Hussh app.

Use when resetting a Kai/UAT test account by email for end-to-end onboarding, vault, RIA, consent, or profile retesting.

Use when evaluating future roadmap ideas, creating planning-only architecture docs, or assessing R&D concepts against Hussh north stars, trust boundaries, and current repo reality.

Use when changing or verifying Kai analytics observability across GA4, Firebase Analytics, BigQuery export, growth dashboard contracts, property and stream topology, or shared-auth versus analytics-plane boundaries.

Use when drafting short community-facing replies for Discord or public chat about hushh-research, Kai, PKM, consent architecture, mobile/native tradeoffs, privacy boundaries, roadmap questions, or repo-based technical Q&A.

Use when working on hussh Research RIA, CRD scraping, or financial verification API integration so Codex reads the canonical RIA Intelligence API docs before changing routes, proxies, tests, or docs.

Use when verifying GitHub contribution attribution, green-dot eligibility, commit author email, PR targeting, and merge readiness for Hussh work so daily contributions land on the intended GitHub profile.

Use when implementing or reviewing Mac-side knowledge connectors (local filesystem, Spotlight, Apple Notes, Apple Mail, Calendar, Obsidian, Notion, Google Drive, Slack) inside the desktop-mac owner family.