wayfinder

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 saved as a markdown file, then works its decision tickets (questions whose resolution is a decision, not slices of a build to execute) 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, with 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. A wall of IDs or URLs is illegible; names read at a glance. A name wraps its link to the corresponding file in the tickets/ directory.

The Map

The map is saved in .agents/scratchpad/[feature-name]/map.md, where [feature-name] is a short kebab-case name representing the effort. When charting a new map, if that feature directory already exists, append a numeric suffix to the feature name (e.g., .agents/scratchpad/[feature-name]-2/map.md). When resuming, use the provided directory path. Its tickets are stored as individual files in the .agents/scratchpad/[feature-name]/tickets/ directory.

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 file, so the map never restates it, only gists it and links.

The map body

The whole map at low resolution, loaded once per session. Open tickets are not listed: they are files in the tickets/ directory, found by reading them or searching their contents using grep_search (e.g. searching for Status: open).

## 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 closed ticket, enough to judge relevance, then follow the link to read the detail the ticket holds -->

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

## Not yet specified

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

## Out of scope

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

Tickets

Each ticket is a separate file in the tickets/ directory; the filename MUST be strictly kebab-case (e.g., ticket-name.md). Its body is the question, sized to one 100K token agent session:

# [Ticket Name]

**Type:** <research | prototype | grilling | task>
**Status:** <open | claimed by subagent-[ID] | closed | cancelled>
**Blocked By:** <other ticket filenames>
**Research Dir:** <target subdirectory for research findings, if applicable>

## Question

<the decision or investigation this ticket resolves>

---

<!-- Resolution will be appended here -->

Each ticket carries a type, one of research, prototype, grilling, task (see Ticket Types).

A session claims a ticket by updating its status in its file to claimed by subagent-[ID] (generating a 6-character random alphanumeric ID if none is assigned), first, before any work, so concurrent sessions skip it. That assignee is the claim: an open status is unclaimed.

Blocking relies exclusively on the Blocked By list (no bidirectional linking is required). A ticket is unblocked when every ticket blocking it is marked as closed; the frontier is the open, unblocked, unclaimed tickets, the edge of the known. Agents must verify the closed status of all exact filenames listed in Blocked By.

The answer isn't part of the question body; it's recorded on resolution (see Work through the map). Assets created while resolving a ticket are linked from the ticket, not pasted in.

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 to surface a fact a decision waits on. Resolved by a subagent that activates the research skill. Use when knowledge outside the current working directory is required. Do not use this type for local codebase design or implementation strategy (use grilling instead). If you assign this type, you MUST populate the Research Dir: field and you MUST delegate it to a subagent. Planning mode does not block research resolution: research subagents should still gather facts, write findings into the assigned research directory, append a ## Resolution block to the ticket, and close it.
• 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) by activating 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): Conversation. The default case. Always activate the grilling and domain-modeling skills.
• 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.

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).

Out of scope

Fog only ever gathers toward the destination. The destination fixes the scope, so work beyond it is out of scope: it isn't fog, and it doesn't belong in Not yet specified. It gets its own Out of scope section on the map: work you've consciously ruled out of this effort. Scope, not sharpness, lands it here.

Out-of-scope work never graduates (the frontier stops at the destination), so it returns only if the destination is redrawn, and then as a fresh effort, not a resumption.

Ruling something out of scope is a scoping act, not a step on the route. When a ticket that already exists turns out to sit past the destination (mis-scoped in while charting, or exposed by a resolution), close it (a closed ticket is unambiguously off the frontier) and leave one line in the Out of scope section: the gist plus why it's out of scope, linking the closed ticket. It stays out of Decisions so far, which records the route actually walked; a scope boundary isn't a step on it.

Invocation

Two modes. Either way, never resolve more than one ticket per session, with the exception of research tickets.

Chart the map

User invokes with a loose idea.

1. Name the destination. Activate the grilling and domain-modeling skills, to pin down what this map is finding its way to: the spec, decision, or change. The destination fixes the scope, so it's settled first.
2. Map the frontier. Grill again, breadth-first this time: fan out across the whole space rather than deep on any one thread, surfacing the open decisions and the first steps takeable now. If this surfaces no fog (the way to the destination is already clear, the whole journey small enough for one session), you don't need a map. Stop and ask the user how they'd like to proceed.
3. Create the map in .agents/scratchpad/[feature-name]/map.md: Destination and Notes filled in, Decisions-so-far empty, the fog sketched into Not yet specified.
4. Create the tickets you can specify now as separate files in .agents/scratchpad/[feature-name]/tickets/, then wire blocking edges by updating the Blocked By lines in those files with exact filenames. Wiring sorts them into the frontier and the blocked; everything you can't yet specify stays in the fog: the Not yet specified section.
5. Fire the research subagents. For each research ticket you just created, write the target research directory path (e.g., research/[ticket-name]) into the ticket file's Research Dir: field. Then, spin up a subagent that activates the research skill to resolve it in parallel, capturing its findings in that pre-defined throwaway directory alongside map.md (see Research ticket resolution rules under Ticket Types).
6. Stop: charting is one session's work; it hand-resolves nothing.

Work through the map

User invokes with a map (directory path). A ticket is optional: without one, you pick the next decision, not the user.

1. Load the map: the low-res view (map.md), not every ticket body.
2. Choose the ticket. If the user named one, use it. Otherwise take the first frontier ticket in order by checking the tickets/ directory (e.g. using grep_search "Status: open"). Claim it: update its status in its file to claimed by subagent-[ID] before any work.
3. Resolve it. Zoom as needed: fetch the full body of any related or closed ticket on demand; activate the skills named in the ## Notes block. If in doubt, activate the grilling and domain-modeling skills. For Research tickets, if the subagent worked in a research/ subdirectory, it must summarize its findings back directly into the ticket file before marking it closed (see Research ticket resolution rules under Ticket Types).
4. Check scope: If the answer reveals that a ticket (this one or another) sits beyond the destination, rule it out of scope and DO NOT append it to Decisions-so-far.
5. Record the resolution: post the answer as a Resolution block at the bottom of the ticket file, change the status to closed, and append a link to the map's Decisions-so-far.
6. Add newly-surfaced tickets (create-then-wire); graduate any fog the answer has made specifiable, explicitly rewriting the Not yet specified section in map.md using the <!-- FOG START --> / <!-- FOG END --> delimiters. If the decision invalidates other parts of the map, DO NOT delete their ticket files; instead, change their status to cancelled or obsolete and remove them from all Blocked By: lists to prevent breaking the dependency graph.

The user may run unblocked tickets in parallel, so expect other sessions to be editing the tickets/ files concurrently. Because each ticket is its own file, collisions are minimized.