jovesun-lab

Generate an interactive node-and-edge diagram as a single standalone HTML file (Arcgram v2). Triggers on: arcgram, interactive/architectural diagram, topology, node graph, flow diagram, system map, dependency graph, workflow diagram, knowledge map, 'show me how X connects to Y', 'visualize this workflow', 'make this a topology', 'build a diagram of this'. Prefer for any system map, dependency graph, topology, or workflow picture even if interactivity wasn't asked for; on a follow-up 'make it inline' / 'show me' / 'render in chat', stay within Arcgram (Mode 1/2), don't switch tools.

Check that an Arcgram diagram's @spec values still match the code that implements it. Reads each node's desc "@spec key=value" line, finds the same-named code constant (hold_ms <-> HOLD_MS / holdMs), diffs the literals. Typed findings: drift, missing constant, non-literal, ambiguous. Reads only the @spec line + named constants, never geometry; marks, never blocks. Run after editing a diagram or its code. Agent-neutral. Sibling to Checkpoint (Checkpoint = structure; Reconcile = values).

Run both Arcgram self-checks in one call. A thin wrapper over Checkpoint (structure) and Reconcile (values): validate(diagram,{code}) runs Checkpoint always and Reconcile when code is supplied, then merges into one source-tagged result in the same {findings,summary,attestation,clean} contract. clean = checkpoint.clean && reconcile.clean. Adds no new check; marks, never blocks. Run after authoring or editing a diagram and its code. Agent-neutral. The single door over its two siblings.

Validate an Arcgram diagram as a logic spec: is the flow well-formed and coherent? Reads node/edge structure (id/f/t/kind/role/type), never geometry. Typed findings - dangling edge, orphan node, missing branch, disconnected island, duplicate id, missing schema, plus optional coherence (every action traces to a goal). Marks, never blocks. Run after authoring or editing a diagram. Agent-neutral. Sibling to Reconcile (Checkpoint = structure; Reconcile = values).

Set up or change notify-me — the plugin that pings the user's phone (via ntfy) and/or plays a sound when an agent is blocked or finished. Use when the user says "set up notify-me", "set up notifications", "notify me when you're blocked", "call me back when you need me", "change the alert sound", "turn the chime on/off", "change my ntfy topic", or when a SessionStart note reports notify-me is installed but not configured.

Throughline keeps the thread of work intact on work that's big enough to drift or that outlives one sitting. Two linked habits: (1) TASK TRACK — an emoji-tagged task list with exactly one ⭐️ MAIN goal anchor, so you can see at a glance whether you're still solving the main thing or have drifted; (2) HANDOFF — compact a session into a plain-markdown handoff doc the next agent (any agent) can pick up cleanly. Reach for it when: a long or many-step task is at real risk of losing the thread, you catch yourself drifting off the original goal, you're wrapping up or running low on context, you're switching agents or sessions, or you're explicitly asked to 'hand this off' / 'write a handoff' / 'summarize for the next session' / 'compact this' / 'pick up where we left off' / 'resume'. Do NOT reach for it on short, self-contained tasks that finish in one pass — the full protocol is overhead there. Capability-agnostic and cross-platform — works as a skill or a plain paste-in prompt.

Measure an AI agent's per-session performance on a small, stable metric set and track it as a trend over a long run, so you can tell whether a change — a new model version, a new operating frame/scaffolding, a new skill set — actually improved the agent or regressed it. Use this whenever someone wants to benchmark, score, grade, or track an agent's performance across sessions; compare two agent versions or frames; build a "did this change help?" scorecard; or turn a finished session into a logged measurement. Triggers on: agent benchmark, session measurement, performance trend, score this session, grade the agent, A/B an agent version, regression tracking for an agent, "is the new model/frame better?", agent report card. Reach for it even if the user just says "measure how that session went" or "track this over time" without naming a metric.