Every principle, skill, plugin, sub-agent, connector and hook this machine loads, under a two-tier model: one global operator layer every session inherits, and project layers that defer to it. Every number is probed from the live machine at build time, never typed.
Slug-named, one idea each, distilled from AI tools in use. A reference to pull from on demand, never pasted wholesale into a prompt. Source: ~/Projects/dotfiles/docs/AI-Principles.md.
Slugs replaced P0NN, so a citation can be sanity-checked where it sits and a merge needs no tombstone stub. The two concrete instructions were carried verbatim: derive from immutable sources and freeze the system for one full cycle. Seven files cited principles by number, not the four the proposal predicted, and all seven were re-pointed in the same change.
The persona and epistemics loaded into every session, in every repo. Project files defer here for operator-level rules.
Auckland. Creators Win (B2C mentorship), WIN·WIN MEDIA (B2B UGC agency), and DHC advisory.
Shortest answer that is still true. Bullets, no preamble, no recap. Fewest tokens that achieve the goal, then stop. Report a finding; don't build the fix unasked.
Current state only. No superseded sections, no strike-throughs, no evolution notes. The past lives in git and chat, never in the document.
Every non-trivial claim tagged confident / best guessing / wildly speculating. Don't round up to certainty; the wobble is information.
A delivery layer under the operator layer: it governs how Claude talks, not how it codes. Installed from alexgreensh/attention-span, switched with /style. The active style costs roughly 900 input tokens per session, cached after the first request (installed range 580–1820).
Terse, warmth stripped, maximum compression. Arrow markers, bold carries the whole answer, no cushioning.
The flagship. Answer first, plain English, expands only on what would cost you a mistake. Warm where Spartan is blunt.
Briefing mode. TL;DR, then a status checklist and tagged next moves. Optimises for scannability over brevity, so it works for standups and fights the shortest-answer rule elsewhere.
The global CLAUDE.md already mandates short, bullets, no preamble. A style adds what prose rules cannot enforce: a format contract. It reaches the main conversation only, so sub-agents answer in default prose.
What this stack can actually do, grouped by the job rather than by how it is delivered. The marker says what backs each one: S skill, P plugin, M MCP server, A sub-agent, C claude.ai connector. Filter the band to see one kind at a time.
Repo standard and docs gates, design and accessibility passes, then a typed Next.js build onto Vercel.
DNS and registrar moves, Workers and Durable Objects, KV/D1/R2, email routing, Turnstile. The one surface with both skills and live MCP behind it.
Connect configuration, billing and tax, key security. Scoped per repo, never global.
Product photos, static and video ads, storyboards, ad scoring and competitor research through the eComrads connector. Pointers only; the recipes live in Notion.
Verify a claim against real papers, audit whether existing citations say what they are cited for. Metered: one credit per fresh run.
Architect layered system prompts, audit against the checklist, adversarial verification, coach a single outgoing prompt.
Mail, calendar, files and the Notion studio, plus a live line into Danny’s own WhatsApp account: read the history, search contacts, send to a person or a group. On top of the connectors: draft a mail in his voice, start a project into Notion tasks, close a task or project, file the week’s newsletters as a digest, send Manawa’s zine, and close the day into Notion (work log, wrap).
Keyword sets, landing-page copy, and finding a skill that already does the job.
Pull GA4 reports for every live site without opening the dashboard, and reach Meta ad accounts from the same session. The GA half is read-only by scope; the Meta half is not yet authorised.
Fan out read-only searches, plan an implementation, answer harness questions. The conclusion returns to the main thread, not the file dumps.
0 of the 47 plugin skills are explicit-invocation only, so the model never offers them; only you typing the command reaches them.
Connectors are a dated claim, not a probe — last checked 2026-08-20. Slack and VoC Sales are gone from the last session checked.
A second plugin surface exists that this build cannot see: claude.ai keeps its own list, and sessions have loaded ecomrads-studio and cowork-plugin-management skills that appear in no local file.
Built-ins are declared, not probed: ~25 harness skills and 6 sub-agents are not enumerable from disk.
The Notion Skills library is the single source of truth for every skill: what is written there is the recipe, and Claude Code, Cowork, claude.ai and the other agents only carry thin pointers that fetch it. This page is only the generated map of what is installed. The list below is a dated claim, not a probe.
The parts that run without you asking, and the parts that only look like they do.
SessionStart → sync.sh
Stop → stop-gate.mjs
Stop → memory-autopush.sh
Stop → stack-drift-hook.sh
UserPromptSubmit → style-reminder.sh
One fact per file, indexed by MEMORY.md. Recall surfaces relevant facts as background context each session. A Stop hook pushes it to git at the end of every session.
The directory holds 9 tasks. 4 are registered and enabled. 0 are orphans: a SKILL.md on disk that the scheduler has never returned.
The scheduler keeps its registry where this build cannot read it, so a task directory can look exactly like a live job while nothing runs it. This page now fails to build if a directory appears that the data file has not classified.
Every build has its own page on mohios.com: the build, the roadmap and what is next. Each repo defers to the operator layer and embeds website-build-rules, re-synced from one source and never hand-edited.
Booking, payments, client portal and admin on one stack. Build page.
The embeddable Mohios chatbot behind the sites. Build page.
Personal site, off Hostinger since 2026-08-14. Build page.
A free directory and newsletter for phone-free events in Auckland. Build page.
The new site for Manawa; Squarespace still serves the domain. Build page.
The portfolio: ten builds, each with its own page. All ten.
Marketing and lead-capture site for NICH Cycling NZ. Build page.
Creators Win (B2C mentorship) and Win Win Media (B2B growth studio): one repo, host-based routing, two apex domains. Creators Win · Win Win Media.
The Website Menu: website elements with wireframes, business value and effort tags. Build page.
Client-ready records of work this stack shipped, written up as a working record first and published second. The build fails if a record named here has moved, so a card can never point at nothing.
A consulting site off WordPress and off its host in one working day — website, DNS, email and the domain registration, four vendors, not one. Zero downtime, no URL changed, annual cost USD 95.88 to 10.46. The sellable half is not the HTML: it is the twelve pre-existing faults the record-by-record pass surfaced (two SPF records, so no SPF; no DMARC; an AAAA record that would have left every IPv6 visitor on the old site) and a cutover order that never risks the mailbox and the website in the same operation.
read the artifact · ~/Documents/Projects/DHC/Clients & Projects/Case-Studies/20260814-Hostinger-Exit-WordPress-Migration.md
GitHub Actions billed ~1,800 minutes a month across the org; rebuilt per-run from the API, about a third of it was rounding on jobs that finished in 13 seconds, because billing rounds each job up to a whole minute. Six repos folded to one job each with filtered triggers, and the fault was fixed in the build-kit template so the next site does not re-buy it. Now ~550. Two repos also had a docs gate and no build gate, which is worse than no CI: the green tick reads as "this builds".
read the artifact · ~/Documents/Projects/DHC/Clients & Projects/Case-Studies/20260822-CI-Minutes-The-60-Second-Line.md
Pushback from the current pass. Replaces the previous set rather than sitting beside it.
Every count is probed at build time; the prose file contains no numbers at all. Claims that cannot be probed carry a visible date instead of pretending to be facts.
The paperclip skills were unlinked from ~/.claude/skills on 24 Aug; they still sit in the repo, so nothing looked broken. They resolve to a warning, not an error, which is why the page shipped dead chips until this pass.
The build fails on a scheduled-task directory the data file has not classified, which catches the next orphan. It cannot catch a task that gets disabled tomorrow, so a green build is not proof the schedule is what you think.