Wayfinder Planning Maps

A loose idea has arrived — too big for one agent session, and wrapped in fog: the way from here to the destination isn't visible yet. Wayfinding is about finding that way, not charging at the destination. This skill charts the way as a shared map, then works its tickets one at a time until the route is clear.

The destination varies per effort, and naming it is the first act of charting — it shapes every ticket. It might be a spec to hand off and iterate on, a decision to lock before planning starts, or a change made in place like a data-structure migration. The map is domain-agnostic — engineering work, course content, whatever fits the shape.

Plan, don't do

Wayfinder is planning by default: each ticket resolves a decision, and the map is done when the way is clear — nothing left to decide before someone goes and does the thing. The pull to just do the work is usually the signal you've reached the edge of the map and it's time to hand off. An effort can override this in its Notes — carrying execution into the map itself — but absent that, produce decisions, not deliverables.

Refer by name

Every map and ticket has a name — its title. In everything the human reads — narration, the map's Decisions-so-far — refer to it by that name, never by a bare id, number, or filename. A wall of 03, 04, 05 is illegible; names read at a glance. The id doesn't vanish — a name wraps its link — but it rides inside the name, never stands in for it.

The Map

The map is the canonical artifact. Its tickets hang off it, one per ticket.

The map is an index, not a store. It lists the decisions made and points at the tickets that hold their detail; a decision lives in exactly one place — its ticket — so the map never restates it, only gists it and links.

Where the map, its tickets, blocking, claims, and frontier queries physically live is adapter-specific. Consult the adapter for this repo before writing anything. Absent one, default to the local-markdown adapter: TRACKER-MARKDOWN.md, which stores the map under .plan/ and states its own shapes, invariants, and verification checklist.

Two rules keep the index honest, because a map that has drifted misleads every session that trusts it, and it does so silently:

• The map gists a decision and links it; a ticket's own facts — its type, edges, status — are read from the ticket, never copied into prose. A gist is lossy on purpose and cannot be derived — that is why the map reads in one pass. A fact copied has two homes, and goes stale in one of them.
• Progress is derived from the tickets — count them when the question is asked, wherever it is asked: a README, a contributor guide, the map itself. Never write the count down. "Four of nine resolved" is true for a week and wrong forever after, and the reader who trusts it cannot tell. A dated handoff is exempt where it records what one session did — that is history, and history never claimed to be current. The exemption stops at the record: an instruction written into a handoff ("claim it by setting…") goes stale exactly like a count, so point at the skill rather than restating it.

The map body

The whole map at low resolution, loaded once per session. Open tickets are not listed here — they are found by querying the adapter.

## Destination

<what reaching the end of this map looks like — the spec, decision, or change this effort is finding its way to. One or two lines; every session orients to it before choosing a ticket.>

## Notes

<domain; skills every session should consult; standing preferences for this effort>

## Decisions so far

<!-- the index — one line per resolved ticket: enough to judge relevance, then zoom the link for the detail the ticket holds -->

- [<resolved ticket title>](<link>) — <one-line gist of the answer>

## Not yet specified

<!-- see "Fog of war": in-scope fog you can't ticket yet; graduates as the frontier advances -->

## Out of scope

<!-- see "Out of scope": work ruled beyond the destination; closed, never graduates -->

Tickets

A ticket's body is the question, sized to one fresh agent session.

A session claims a ticket, first, before any work, so concurrent sessions skip it. How a claim is expressed, and how a dead session's stale claim is told apart from live work, is the adapter's business.

Blocking is a ticket's list of the tickets it waits on. A ticket is unblocked when every ticket it lists is resolved; the frontier is the open, unblocked, unclaimed tickets — the edge of the known. Prefer an adapter whose blocking is native, because it renders the frontier visually in the tracker's own interface, and the human sees what's takeable without opening the map.

out_of_scope is closed, and closed is not resolved: it satisfies no blocking edge. A ticket blocked by an out-of-scope ticket therefore never unblocks — one of the two is mis-scoped, and you should say which.

The answer isn't part of the body as written — it is recorded on resolution. Assets created while resolving (research notes, prototype code) are saved in the repo and linked, not pasted in.

Undermined decisions

A resolved ticket sometimes rests on a premise that a later ticket destroys. Mark it and say what broke: record the ticket that broke it, and open its answer with a line saying so. The decision still stands — nobody has reopened it — but every session that reads the map can now see what it is standing on. A decision recorded as simply resolved reads as settled, and that is how a live problem gets laundered into a checkmark.

Ticket Types

Every ticket is either HITL — human in the loop, worked with a human who speaks for themselves — or AFK, driven by the agent alone. A HITL ticket only resolves through that live exchange; the agent never stands in for the human's side of it (a grilling agent that answers its own questions has broken this).

• Research (AFK): Reading documentation, third-party APIs, or local resources like knowledge bases. Use the research skill: investigate against primary sources and create a cited markdown summary as a linked asset. Use when knowledge outside the current working directory is required.
• Prototype (HITL): Raise the fidelity of the discussion by making a cheap, rough, concrete artifact to react to — an outline, a rough take, a stub, or UI/logic code via the prototype skill. Links the prototype as an asset. Use when "how should it look" or "how should it behave" is the key question.
• Grilling (HITL): A relentless interview — one question at a time, a recommended answer offered with each, decision branches resolved one by one, facts looked up rather than asked — with the domain-modeling skill applied so terms and decisions are captured as they crystallise. The default case.
• Task (HITL or AFK): Manual work that must happen before a decision can be made — nothing to decide, prototype, or research, but the discussion is blocked until it's done. Signing up for a service so its API can be judged, provisioning access, moving data so its shape can be seen. This is the one type that does rather than decides — and it earns its place by unblocking a decision, not by delivering the destination. The agent drives it alone where it can (AFK); otherwise it hands the human a precise checklist (HITL). Resolved when the work is done; the answer records what was done and any resulting facts (credentials location, new URLs, row counts) later tickets depend on.

Fog of war

The map is deliberately incomplete: don't chart what you can't yet see. Beyond the live tickets lies the fog of war — the dim view of decisions and investigations you can tell are coming but can't yet pin down, because they hang on questions still open. Resolving a ticket clears the fog ahead of it, graduating whatever's now specifiable into fresh tickets — one at a time, until the way to the destination is clear and no tickets remain.

The map's Not yet specified section is where that dim view is written down: the suspected question, the area to revisit later. It's the undiscovered frontier toward the destination — everything here is in scope, just not sharp enough to ticket. Write as loosely or as fully as the view allows; it doubles as a signpost for collaborators reading where the effort is headed.

Each patch carries a title and, where you know which open ticket will clear it, an anchor. A title names a question no live ticket holds; a question tracked both sharply and vaguely rots in its vague copy.

Fog or ticket? The test is whether you can state the question precisely now — not whether you can answer it now.

• Ticket when the question is already sharp — even if it's blocked and you can't act on it yet.
• Not yet specified when you can't yet phrase it that sharply. Don't pre-slice the fog into ticket-sized pieces: it's coarser than a ticket, and one patch may graduate into several tickets, or none, once the frontier reaches it.

Not yet specified excludes what's already decided (Decisions so far), what's already a live ticket, and what's out of scope (the next section).