Open canon
Take the artefacts
All 154 artefacts that run the system, as plain markdown — the same files the agents read. No sign-up, no licence theatre. They are written for one practice; the ideas travel. Start with core-operating-model if you want the shape, or skill-exec if you want to see an agent's working instructions.
154 artefacts
agent-aide
agent
Profile for Aide (label A1-DE) — the Owner-serving personal chief-of-staff: sweeps the committed cycle for what needs Aled, sizes it, and books it into his calendar hold windows (bounded auto-hold: unattended within t…
agent-atlas
agent
Profile for Atlas (label ATL-4S) — planning and strategy: goals, prioritisation, and cycle commitment
agent-content-engine
agent
The three-stage content pipeline that turns raw work evidence into publishable content — truth capture, then case study, then article
agent-forge
agent
Profile for Forge (label F0-RGE) — implementation: builds a ticket and opens a PR, never merges
agent-pixel
agent
Profile for Pixel (label P1-XEL) — brand and design: the design system, brand identity, design exploration, and visual production across the ventures
agent-prism
agent
Profile for Prism (label PR-1SM) — review and quality: the independent verdict and good-to-merge signal
agent-pulse
agent
Profile for Pulse (label PUL-5E) — ops and self-improvement: parity, friction capture, task health, optimisation review, and the model-and-schedule efficiency of the scheduled layer; propose-only
agent-reach
agent
Profile for Reach (label R3-ACH) — marketing and go-to-market: strategy, content, channels, lifecycle, and discovery across the ventures
agent-relay
agent
Profile for Relay (label R3-LAY) — delivery management: triage, routing, blocker resolution, and the post-approval merge
agent-roster
agent
Index of the os.Claude Layer 3 fleet — the functional agents and the vertical operators, their labels, roles, and profile files
agent-scout
agent
Profile for Scout (label SC-0UT) — pipeline: captures people and opportunities into Linear and qualifies them
agent-sonar
agent
Profile for Sonar (label SO-N4R) — design strategy, discovery and service design: building a consulting-grade understanding of who a venture serves, the jobs they are trying to do, and how well the experience and serv…
convention-aesthetic
convention
The cross-venture aesthetic canon — Aled's visual sensibility above the per-venture brand entries: written taste principles, named references and why, anti-patterns, and pointers to the Figma reference library
convention-agent-runtime
convention
How a Layer 3 role becomes a running worker — the execution substrate the org model deliberately left unnamed, now in ad-hoc use
convention-analytics
convention
Conventions for web analytics and consent in Aled's system — the consent posture chosen by site type (personal/portfolio vs commercial), the tracking approach that follows from it, and what requires human action
convention-artefact-format
convention
The house format for every canon artefact — the frontmatter schema and the section skeleton each artefact type follows (skill, task, routine, agent, operator, assistant, convention, core, workflow, playbook)
convention-audit
convention
The audit apparatus Sonar uses to open an engagement — the category sets per audit type (App, Design System, Team, the technical/sourcing-feasibility audit, and the conversion-diagnostic variant) and the four-card lad…
convention-brand
convention
The per-domain brand and identity standard for Aled's ventures — what every domain's brand definition must specify (positioning, voice, palette, type, logo, imagery, design-system pointer), with BARA and A1 as the ins…
convention-comms-owner
convention
The standard for anything an agent puts in front of the Owner to read or act on — the scannable decision-and-action header, the plain-language escalation that leads with a recommendation, the standing operator report…
convention-decision-log
convention
The tool-agnostic standard for the decision log — what it records, the index-plus-weekly-child-documents structure, the entry format, and the lifecycle (append newest-first, one entry per decision, update rather than…
convention-deck
convention
The house slide-deck design system — the slide archetype library and its weight tiers, the treatment library harvested from the TMS files (named treatments inside the archetypes, with build patterns), the fixed grid a…
convention-deck-narrative
convention
Defines each deck narrative structure — when to use it, section order and job, slide-count split, opening and closing instruction, proof placement, the detection signal that identifies it in an existing deck, the eval…
convention-document-opening
convention
How a client-facing prose document opens — the fixed stack of title, byline, headline, governing thought and TL;DR, with the criteria a governing thought must meet and the drafting technique that reaches one without b…
convention-figma
convention
Conventions for Figma in Aled's system — which connector writes, the Figma rulebooks that must be loaded before any write (figma-use always; figma-generate-library for component work; figma-generate-design for a page…
convention-github
convention
Conventions for GitHub in Aled's system — repos in scope, which surface may touch a repo (Forge's lane versus a credential-less session), branch naming, PR structure, GitHub MCP usage and read-volume safety, running b…
convention-hold-windows
convention
The first-class convention for Aled's calendar hold windows — the reserved recurring blocks Aide books his committed work into
convention-host-access
convention
How an interactive Cowork or Claude session reaches — or structurally cannot reach — an always-on host, and what to do instead
convention-lean-discovery
convention
The lean discovery kit Sonar reaches for when a full engagement-kickoff is too heavy for a first pass — a minimum-viable set of four artefacts (actor card, who-does-what map, findings + opportunities, lean prioritisat…
convention-linear
convention
How Aled's work is expressed in Linear specifically — the teams and projects, the issue states per workflow, the label taxonomy, the agent single-select group and its routing values (including the lowercase operator-p…
convention-mrp-voice
convention
The Mr Pritchard editorial voice — the register, anchors, and drafting discipline that Mr Pritchard's Guide to Design is written in
convention-mux
convention
Conventions for Mux video in Aled's system — the per-project environment model, the setup sequence for standing up a dedicated Mux environment and least-privilege credentials, the Vercel/Sanity wiring, playback defaul…
convention-naming
convention
The naming taxonomy for everything above the canon-artefact line — verticals, ventures, operators, Linear teams, projects, initiatives, documents and decision-log slugs
convention-project-status
convention
How a project moves through its statuses and how its health is reported, independent of the tracker — the lifecycle and what each status means, Hold as a real parked state, native project status updates as the backbon…
convention-retail
convention
The shared retail and e-commerce model for Aled's ventures — the customer touchpoint chain from discovery to repeat and referral and what each step must do, the retail KPI vocabulary beyond convention-shopify (gross a…
convention-sanity
convention
Conventions for Sanity CMS in Aled's system — projects in scope, the Studio version baseline and what the current major changed, schema setup, naming standards, field UX, and deployment
convention-secrets
convention
How credentials and secrets are named, stored, and defaulted across Aled's projects — env vars only with .env.local gitignored and .env.example committed, service-namespaced names, fail-loud on a missing variable, the…
convention-shopify
convention
Conventions for Shopify in Aled's system — store in scope, the connector-vs-theme split, product and collection naming, discounts and inventory, the ShopifyQL queries that define each KPI, and what requires human action
convention-storybook
convention
Conventions for Storybook and visual regression in Aled's system — the three build modes (code-first, design-first, build-then-refine) declared per project or per feature and the reference each one names, the build-fi…
convention-ticket
convention
How work is written and run as tickets in Aled's system, independent of the tracker — the standard ticket shape, the capture-then-refine-then-ready discipline, the evidence-first capture format, Pattern A folded valid…
convention-user-modelling
convention
The shared definitions for the user-modelling toolkit Sonar uses to understand who a venture serves and why they do or don't convert — the artefacts (segment, archetype, persona, JTBD, forces, opportunity solution tre…
convention-vercel
convention
Conventions for Vercel in Aled's system — projects in scope, deployment setup, environment variable naming, and what requires human action
core-operating-model
core
The canonical reference for how Aled's AI operating layer is structured — the six layers (inputs, skills, scheduled, agents & operators, workflows, governance), what each is, and the rules that distinguish them
operator-a1
operator
The Operator of the A1 vertical — the Association of One consultancy, owned end-to-end within a granted mandate: the practice itself (a1.OS standards and playbooks, a1.Brand) plus the live client engagements as sub-ma…
operator-apps
operator
The Operator of the Apps accelerator — a portfolio vertical, not a single outcome: bets resolved live from Linear, run as a digital factory that allocates finite fleet capacity across them and moves each toward effici…
operator-bara
operator
The Operator of the BARA vertical — owns BARA's relaunch outcome end-to-end within a granted mandate, commanding the functional fleet through Relay and reporting to the Owner
operator-bottrader
operator
The Operator of the bot.Trader vertical, and the Orchestrator layer of its four-layer model — the Scout layer explores and generates hypotheses, the Researcher gate and gauntlet rule on them, the Orchestrator routes,…
operator-mrp
operator
The Operator of the Mr Pritchard vertical — the editorial / personal-brand practice, owned end-to-end within a granted mandate: build one connected design-leadership position in public, one argued piece at a time, and…
playbook-client-onboard
playbook
The prescribed sequence for opening a new A1 client engagement — create the client project under the A1 team, frame the engagement (advisory-led by default), scaffold the per-client decision log, set up the phase/mile…
playbook-engagement-kickoff
playbook
The prescribed sequence for kicking off and running a Sonar engagement — lock the spine and actor, model the audience and where we win, map content and belief, blueprint the service, synthesise opportunities and gaps,…
playbook-project-setup
playbook
The prescribed sequence for standing up a new project of any kind, not only a website: a short intake interview that establishes the configuration (website or not, public or private, framework, CMS, hosting, domain an…
playbook-prototype-config-panel
playbook
The prescribed response when a design decision turns on feel — interaction and motion values such as durations, easings and offsets — that a static ticket, a comment or a screenshot cannot carry: deliver a live config…
playbook-store-launch
playbook
The prescribed sequence for taking a retail venture from brand definition to a live Shopify store — strategy, brand, range and product data, storefront, packaging, flows and newsletter, channels and SEO, launch, first…
routine-feasibility-loop
routine
Driver routine for bot.Trader Mandate A's feasibility pipeline — grinds every ready Phase-2b feasibility-study ticket in one operator-triggered batch, composing skill-feasibility-study per ticket: fetch real venue dat…
skill-architecture-spike
skill
Research and specify a technical approach before any code is written, on behalf of the Forge role
skill-attention-sweep
skill
Sweep the committed cycle for everything that needs Aled and size it
skill-audience-icp
skill
Define and refine the target audience — ideal customer profile and segments — for a domain
skill-brand-system
skill
Define and maintain a domain's design system and brand identity — palette, type, logo usage, art direction, photography guidelines and components — and read or score an existing system before working in it
skill-campaign-report
skill
Measure marketing performance against KPI targets and report movement in plain language
skill-channel-ops
skill
Reach's channel operating procedure for a retail venture — how a planned, approved action reaches a live channel and what each channel needs to run
skill-content-article
skill
Placeholder for the proposed procedure for writing long-form articles for the careerOS writing surface and downstream syndication — grounding the argument in a truth capture or playbook, holding the voice, and avoidin…
skill-content-case-study
skill
Placeholder for the proposed procedure for writing a careerOS case study from a truth capture — picking the format (snapshot, full, article, or cv-entry), applying the writing standard, and validating against the qual…
skill-content-studio
skill
Plan and draft marketing content in a domain's own voice — email, social posts, product and listing copy, landing-page copy, ad copy
skill-content-tov
skill
Placeholder for the proposed careerOS tone of voice — calm, precise, structurally confident, sentence case, British spelling, outcome before adjective, no marketing-speak
skill-content-truth-capture
skill
Write a truth capture — a traceable record of what actually happened in a piece of real work, produced from the source thread and never from memory, so a case study or article downstream argues from evidence rather th…
skill-conversion-diagnostic
skill
Diagnose where qualified users leak from a venture's funnel — build the stage spine, overlay the forces-and-barriers conversion engine, and find the leaks against the one or two metrics that matter, surfacing each gap…
skill-creative-brief
skill
Turn a need into a creative brief and, where possible, into first assets — translating a campaign, page or product requirement into clear direction for design
skill-deck-narrative
skill
Selects a narrative structure for a deck by purpose, executes it as an action-title outline against the structure's definition in convention-deck-narrative, and evaluates an existing deck against whichever structure i…
skill-deck-parity
skill
Review a produced deck against convention-deck and its approved narrative outline, and write a plain-language verdict Aled can act on without opening the file
skill-design-exploration
skill
Pixel's divergent mode — deconstruct a concept and reimagine it as differentiated, contemporary identity directions across print, merch, OOH, and digital
skill-design-parity
skill
Review a UI build against its intended design and write a plain-language verdict Aled can act on without reading the code
skill-design-review-round
skill
Run a design review round from a design tool's comments to agreed, ticketable work — capture every Figma (or other design-tool) comment of a review round into one dated Linear document with its text, the element it si…
skill-design-tokens
skill
Maintain design tokens, component libraries and the Figma-to-code bridge for a domain — the machinery that keeps design and build in sync
skill-discovery-audit
skill
Run a discovery audit at the start of an engagement — assess a venture against a chosen category set, capture each observation as a Finding card, cluster the findings into Theme Summaries with root cause and How-Might…
skill-dispatch-run
skill
Run a single Todo ticket through whichever connector-surface agent owns it — Pixel, Reach, Sonar, Scout, or Aide — the Cowork-surface sibling of skill-exec
skill-exec
skill
Execute a Claude Code ticket end to end and open a pull request for review, on behalf of the Forge role
skill-feasibility-study
skill
Assess whether a proposed bot.Trader strategy is worth validating before any build begins — establish the structural advantage it claims, confirm regulatory and venue feasibility, model the costs it must clear, and re…
skill-fleet-dispatch
skill
Sweep Todo across all active delivery projects for tickets owned by the connector-surface fleet — Pixel, Reach, Sonar, Scout, Aide — test each candidate for eligibility (a leaf, no open blocked-by relation, no unmet d…
skill-goal-review
skill
Periodic review of progress against the outcome-initiatives and their KPIs across all ventures
skill-gtm-plan
skill
Turn a strategy and KPI tree into a go-to-market plan — channels, messages and a campaign calendar — for any domain
skill-issue-capture
skill
Inline-callable procedure that files a Backlog ticket in Apps / os.Claude when a skill hits an unexpected problem
skill-launch-campaign
skill
Reach's procedure for a product drop, a store launch or a relaunch — the one campaign shape a 0→1 retail brand runs repeatedly
skill-lifecycle
skill
Reach's procedure for the automated flows that turn a first buyer into a repeat one — the standard flow set (welcome, browse, cart and checkout abandonment, post-purchase from confirmed to review ask, replenishment an…
skill-moodboard
skill
Assemble a curated mixed-media moodboard that presents one visual direction as a designed artefact, in the register of a contemporary studio reveal
skill-newsletter
skill
Reach's procedure for building and running a retail venture's editorial newsletter — the send people open because it reads like a journal, not a store — beside the automated flows in skill-lifecycle
skill-operating-loop
skill
The operator's standing cycle, run in the context of a single vertical — read the goal and KPIs, assess against target, decide the next best actions, dispatch through Relay to the functional fleet, escalate only at th…
skill-opportunity-eval
skill
Evaluate a new opportunity — a venture, a role, a bet, a partnership — against current strategy, goals and capacity, and produce a structured decision brief
skill-ops-retro
skill
Turn friction observed while running the operator's skills, tasks, and routines into ready-to-add canon artefacts — a new or updated skill, task, routine, convention, or agent profile the operator saves
skill-ops-sync
skill
Audit parity between the Claude-side saved artefacts (canon) and the claude-ops repo (published mirror), and raise publish tickets where Claude is ahead so the agents site and the remote routines build from current so…
skill-optimisation-review
skill
Periodic Pulse review that keeps Aled's tooling conventions current, his operating shape sound, and his scheduled layer efficiently run, raising proposals into the os.Claude Backlog
skill-outreach-draft
skill
Draft personalised outreach and follow-up messages in Aled's voice for a Network contact or a Pipeline opportunity, from the context skill-pipeline-sweep already captured
skill-packaging-unboxing
skill
Pixel's procedure for designing the physical arrival of an order as one brand surface — outer pack, inner wrap, inserts (care card, thank-you, maker story, a Welsh sign-off where earned), labels and the sustainability…
skill-pipeline-qualify
skill
Qualify Pipeline tickets from Backlog to Ready on behalf of the PM role
skill-pipeline-sweep
skill
Run a scheduled Gmail-to-Linear sweep that captures inbound pipeline mail into Aled's Pipeline team — people into Network, opportunities into Roles
skill-portfolio-allocation
skill
The allocation decide-step for a portfolio operator — how operator-apps decides across its bets instead of driving one goal to a target
skill-prioritise
skill
Turn findings, themes, and opportunities into a scored, sequenced plan — apply the prioritisation standard (severity, or Impact × Effort × Confidence with the confidence overlay), output a ranked table and an Impact ×…
skill-product-design
skill
Design product and UI against a design system — screens, flows and components for the digital products
skill-qa
skill
Review a Claude Code pull request for Aled and write a plain-language verdict he can act on without reading the code
skill-retail-strategy
skill
Set or refresh a retail venture's business strategy — category and positioning, range architecture, price architecture, channel sequence by stage, and the retail calendar — as the retail layer beneath skill-strategy-c…
skill-security-review
skill
Review a Claude Code pull request for security risks and write a plain-language verdict Aled can act on without reading the code
skill-seo-discovery
skill
Reach's discoverability procedure for a retail venture — making its products findable by the people its ICP describes, on the surfaces where they look
skill-service-blueprint
skill
Build a service blueprint — lay a stage spine across the evidence, customer, frontstage, backstage, and support lanes, connect the actor's traversal to the service stack behind it, colour-code confidence, and flag the…
skill-storefront-merchandising
skill
Pixel's commerce-design skill — score a storefront against standard-storefront, then design and merchandise each surface (homepage, collection, product page, cart and checkout, order comms) against that bar and the co…
skill-strategy-cascade
skill
Turn a venture's stated goal into a strategy cascade — one strategy statement, a small set of objectives, and a measurable KPI tree with named targets and baselines — expressed as Linear outcome-initiatives
skill-strategy-charter
skill
Engage Aled to set an area's purpose, mission, who it serves, and vision of winning — the strategic intent that skill-strategy-cascade turns into measurable objectives and KPIs
skill-task-health
skill
Verify the scheduled layer is healthy on three axes — behaviour (each task still produces its expected output), deployment parity (every canon task/routine artefact has a live schedule that fires on its cadence, and e…
skill-telemetry-capture
skill
Read a run's own session transcript, extract one telemetry record against schema v1, and write it to Drive as the run's closing act
skill-triage
skill
Triage and project-manage Linear tickets in the operator's delivery projects on behalf of the Claude Code PM role
skill-unit-economics
skill
The operator's procedure for working out whether a retail venture makes money per order and what a pound of spend should return — the per-order margin ladder from price to contribution margin, acquisition economics (C…
skill-user-modelling
skill
Produce the user-modelling artefacts for a venture — segment, persona, JTBD layers, forces, opportunity solution tree, behavioural modes, scenarios — one artefact per job, grounded in research and tagged known/assumed…
skill-visual-production
skill
Produce on-brand visual assets from a brief — social and ad creative, page and email graphics, product imagery layouts, decks and documents
standard-design-system
standard
The quality bar a design system must clear — token architecture, naming and three-way name alignment, component hierarchy, binding discipline, coverage, documentation, accessibility (WCAG 2.2 AA, stated as run checks)…
standard-prioritisation
standard
The fleet's quality bar for ranking work — severity tiers for audit and release-gating work, Impact × Effort × Confidence scoring for roadmap and intervention work, cost of delay ÷ size (WSJF) for the queue waiting on…
standard-storefront
standard
The quality bar an e-commerce storefront must clear — the anatomy and bar per surface (homepage, collection, product page, cart and checkout, account and order status, search and navigation, empty states), trust and c…
task-a1-operator-loop
task
Weekly thin loader that runs skill-operating-loop in the context of the A1 vertical — the Association of One practice plus its live client engagements — on behalf of operator-a1
task-a1-operator-standup
task
Daily thin loader that runs the shadow stand-up (tactical daily pass of skill-operating-loop steps 1-6 over yesterday) for the A1 vertical on behalf of operator-a1, feeding Aled's 09:00 stand-up
task-aide-loop
task
Weekly thin loader that runs Aide's attention loop on behalf of agent-aide — sweep the committed cycle for what needs Aled, allocate the week, and propose calendar holds inside his declared hold windows
task-apps-operator-loop
task
Weekly thin loader that runs the operating loop for the Apps accelerator on behalf of operator-apps — a portfolio, so the decide-step is allocation across bets (skill-portfolio-allocation), not driving one goal
task-apps-operator-standup
task
Daily thin loader that runs the shadow stand-up (tactical daily pass of skill-operating-loop steps 1-6 over yesterday) for the Apps accelerator on behalf of operator-apps, feeding Aled's 09:00 stand-up
task-bara-operator-loop
task
Weekly thin loader that runs skill-operating-loop in the context of the BARA vertical, on behalf of operator-bara
task-bara-operator-standup
task
Daily thin loader that runs the shadow stand-up (tactical daily pass of skill-operating-loop steps 1-6 over yesterday) for the BARA vertical on behalf of operator-bara, feeding Aled's 09:00 stand-up
task-bottrader-operator-loop
task
Weekly thin loader that runs skill-operating-loop in the context of the bot.Trader vertical, on behalf of operator-bottrader
task-bottrader-operator-standup
task
Daily thin loader that runs the shadow stand-up (tactical daily pass of skill-operating-loop steps 1-6 over yesterday) for the bot.Trader vertical on behalf of operator-bottrader, feeding Aled's 09:00 stand-up
task-bottrader-watch
task
Daily sensor for the bot.Trader runtime, on behalf of operator-bottrader — reads the health digest the GitHub Actions decision cycle publishes outbound (heartbeat outcome and the guard's own last-write timestamp, dail…
task-content-drain
task
Weekly Mr Pritchard content qualify pass — works through the new captures (decisions, moments, breakthroughs, opinions) and asks of each "what is this, and is it worth publishing?" Worth it → flesh into a stated posit…
task-content-review
task
Monthly Mr Pritchard capture review — sweeps the parked captures the weekly qualify pass set aside and asks whether they now cluster, by theme, into something shareable that no single one was on its own
task-coordinate
task
Scheduled deployment of skill-coordinate — the Relay (R3-LAY) cross-board PM coordination pass
task-cycle-planning
task
The cycle-boundary ceremony, run as a scheduled task — retro the closing cycle, roll over incomplete work, and propose the next cycle's commit and its one goal, with Aled the gate on cycle membership and goal
task-daily-report
task
Morning brief on delivery work — an agnostic status-and-progress report over active work only, posted as one short Linear project status update per live project with an explicit health flag, so projects carry the dail…
task-fleet-dispatch
task
Scheduled deployment of skill-fleet-dispatch — sweeps Todo across delivery projects for tickets owned by the connector-surface fleet (Pixel, Reach, Sonar, Scout, Aide) and runs each via skill-dispatch-run
task-goal-review
task
Scheduled deployment of skill-goal-review — the periodic read of progress against the outcome-initiatives and their KPIs across every venture
task-health
task
Scheduled deployment of skill-task-health — the Pulse health check on the scheduled layer (behaviour, deployment parity, config parity)
task-mrp-operator-loop
task
Weekly thin loader that runs skill-operating-loop in the context of the Mr Pritchard editorial vertical, on behalf of operator-mrp
task-mrp-operator-standup
task
Daily thin loader that runs the shadow stand-up (tactical daily pass of skill-operating-loop steps 1-6 over yesterday) for the Mr Pritchard editorial vertical on behalf of operator-mrp, feeding Aled's 09:00 stand-up
task-ops-sync
task
Scheduled deployment of skill-ops-sync — the Claude→claude-ops parity audit
task-optimisation-review
task
Scheduled deployment of skill-optimisation-review — the periodic Pulse review of tooling conventions, operating shape, and the model-and-schedule efficiency of the scheduled layer
task-owner-standup
task
Relay's weekday consolidation of the five operator stand-ups into the one 09:00–09:30 stand-up Aled attends
task-pipeline-graduation
task
Pipeline graduation (Scout) — promote surfaced:* Network contacts into the right opportunity funnel (Roles/Advisory/Pitches), link back, mark surfaced:done
task-pipeline-qualify
task
Scheduled deployment of skill-pipeline-qualify (Scout) — qualify Pipeline Backlog tickets to Ready
task-pipeline-sweep
task
Scheduled deployment of the Gmail→Pipeline sweep (Scout) — runs skill-pipeline-sweep once per intake (network, recruiters, roles, advisory)
task-platform-watch
task
Monthly Pulse scan for newly-shipped platform capability the fleet could adopt — Claude Code and Agent SDK release notes only — filing a propose-only FRICTION note to the Pulse queue for each feature worth assessing,…
task-pulse-refine
task
Scheduled deployment of skill-ops-retro's refine pass — the first of the two daily Pulse-retro passes, and the one that owns every read and judgement call
task-pulse-retro
task
Scheduled deployment of skill-ops-retro's author pass — the second of the two daily Pulse-retro passes, and the one that only produces and presents
task-strategy-review
task
Weekly Atlas strategy review — sweeps every venture's outcome-initiative for a complete strategy (purpose, objectives, KPI tree with baselines and targets) and for drift, and raises a surfaced gap ticket to Aled for e…
workflow-cycle-planning
workflow
The cycle-planning workflow — the standing Layer 4 path a cycle boundary flows through: Atlas retros the closing cycle, rolls over incomplete work, and proposes the opening cycle's commit, with Aled as the gate on cyc…
workflow-delivery-loop
workflow
The delivery workflow — the standing path every build ticket flows through, from Backlog to Done, composing the Relay, Forge and Prism behaviours across the triage, build, review and merge stages with the operator as…
workflow-venture-operating-loop
workflow
The standing cycle an operator drives its vertical through — read goal and KPIs, assess, decide, dispatch to the functional fleet via Relay, gate at the mandate edge with the Owner, execute, report, repeat