Keep the operator's understanding from falling behind what their agents ship — the gap between what the vault and repos contain and what the operator actually grasps. Use when agents (spawned workers, overnight sessions, autonomous loops, /aios:update self-modification) have shipped work the operator didn't author, when deciding whether to trust an autonomous loop, when a repo or venture starts feeling opaque, or during /close-session and /aios:housekeeping. The defensive complement to Arc sessions — arcs build understanding as work happens; this guards it from eroding when agents outrun the operator.
Govern shared resources well using Elinor Ostrom's design principles for the commons — applied to AIOS shared substrate: multi-operator vaults, collaboration spaces, company-synced infrastructure, and multiple agents writing one git repo. Use when designing rules for a shared space, deciding who-decides-what across collaborators or agents, preventing tragedy-of-the-commons or write-collision dynamics, setting boundaries on a shared repo/folder, or standing up collab/company governance. Distributed authority done right, grounded in governance science rather than top-down control.
Treat the operator's capacity, pace, and rhythm as first-class design inputs — not afterthoughts to optimize away. Use when planning workload or cadence, deciding whether to push hard or pace deliberately, judging whether carried/slow/deferred work is genuine avoidance vs. a legitimate quality gate or rhythm, designing rituals and routines, sequencing a heavy week, or guarding against burnout-by-velocity. The generative complement to the system's defensive anti-values: it says what conditions let work (and the person doing it) sustain, not just what to never become.
Compose a team (of people OR agents) by lifecycle posture, not job title, using the five product archetypes — Prototyper, Builder, Sweeper, Grower, Maintainer — and the rule that a healthy mix depends on product stage. Use when deciding which agents/people to deploy on a project, diagnosing why a team or agent bundle feels lopsided (all builders, no maintainers), choosing what posture to take on a given piece of work, staffing a pre-PMF vs growing vs mature product, or selecting an agent mix in /7plan or /emerge. The team-composition complement to leverage-points: leverage-points says WHERE to intervene; this says WITH WHAT POSTURE.
Decide WHERE to intervene in a system for maximum effect using Donella Meadows' leverage-points lens — push interventions toward high-leverage places (goals, rules, self-organization, paradigm) and away from low-leverage ones (parameters, buffers, taxes/subsidies). Use when choosing where to act on a complex system, prioritizing competing fixes, designing a policy/intervention/process change, diagnosing why a problem keeps recurring despite effort, or when a past fix didn't stick. The systems-science sharpening of "fix the system, not the symptom."
Turn a structured document (an /ingest reflection, role report, weekly-learnings digest, deck outline, research note) into a beautiful, self-contained HTML infographic — a visual one-pager — with brand-aware theme selection. Use when the user asks to "make an infographic," "visualize this note/report," "turn this into a one-pager/poster," or accepts the post-ingest "generate a visual infographic?" offer.
Turn data into compelling narratives + effective dashboards. Use when presenting analytics to stakeholders, designing KPI dashboards, structuring an executive summary around metrics, building data visualizations, or implementing real-time monitoring patterns.
Python best practices across design patterns, error handling, project structure, and testing. Use when writing Python code, structuring new Python projects, designing APIs for libraries, implementing error handling, or setting up pytest test suites.