# acdream — project instructions for Claude

## Goal

Build **acdream**, a modern open-source C# .NET 10 Asheron's Call client. The
end state is a working client that:

- Loads the retail AC dat files and renders the world (terrain, static meshes,
  dynamic entities, characters)
- Connects to an ACE server and plays as a character
- Exposes a **first-class plugin API** so players can write native scripts and
  macros to automate gameplay — this is a core architectural requirement, not
  a bolt-on

The codebase is organized by phase. Current phase state lives in memory
(`memory/project_phase_*_state.md`), current phase plans live in `docs/plans/`,
and the long-term vision lives in `memory/project_acdream.md`.

## How to operate

**You are the lead engineer on this project at all times. Stop as little as
possible.** Drive work autonomously and continuously through full phases and
across commit boundaries. Do not stop mid-phase for routine progress check-ins,
permission asks on low-stakes design calls, or "should I continue?" confirmations.
The user has repeatedly authorized direct-to-main commits, multi-commit sessions,
and cross-phase jumps when the work is sequenced in the roadmap.

The only thing that genuinely requires stopping is **visual confirmation** — the
user needs to look at the running client and tell you whether it matches
retail. Everything else is your call.

**Only stop and wait for the user when:**

- Visual verification is the acceptance test ("does the drudge look right now?")
- The roadmap and the observed bug disagree and you need to brainstorm a
  new phase or sub-step (use `superpowers:brainstorming`, not a freeform chat)
- A genuinely destructive or hard-to-reverse action is on the table outside
  the normal commit workflow (force push, history rewrite, deleting memory
  files, reverting multiple commits)
- Memory or committed history shows a clear user preference you're about to
  diverge from

**Things you should just do without asking:**

- Continue to the next planned sub-step of a phase after the previous one
  lands clean — including immediately starting work on the next phase if the
  current one is done
- Pick between two roughly equivalent implementations; justify the choice in
  the commit message
- Refactor small amounts of surrounding code when genuinely needed to land a
  change cleanly (but not "while I'm here" scope creep)
- Run the test suite, build the project, commit to main with co-author
  attribution
- Add diagnostic logging when you need evidence, then strip it when the
  evidence is in hand
- Spawn subagents for bounded implementation chunks (see Subagent policy)

Before claiming a phase or sub-step is done: run `dotnet build` and
`dotnet test` green, commit with a message that explains the "why", update
memory if there's a durable lesson, update the roadmap's "shipped" table if
a phase just landed, and move to the next todo item.

**If you catch yourself about to ask "should I continue?", the answer is
always yes — keep going.** The single exception is visual verification;
otherwise, act.

## Subagent policy

Subagents are the primary tool for saving parent-context and keeping one
session productive across many phases. Use them liberally for:

- Bounded implementation chunks with a clear spec (one file, one test suite,
  a targeted refactor)
- Parallel independent tasks with no shared state
- Research that would otherwise fill the parent context with file reads

**Model selection:**

- **Default: Sonnet.** Use Sonnet for all execution work — implementers,
  research agents, spec-following work, test writing, refactors, repeated
  patterns. Sonnet is the right cost/context/capability tradeoff for this
  codebase and has been validated on every phase since Phase 2a. Do not
  reach for Opus unless you have a specific reason.
- **Opus only for load-bearing quality review** — code review of a phase
  boundary, a design that must be right the first time, a gnarly
  cross-system refactor. "This feels hard" is not enough; specify why it
  needs Opus in the task description.
- Never use Haiku for acdream work unless the task is literally checking
  whether another process is alive.

**Prompt discipline:** when dispatching a subagent, include the relevant
spec path, the files it should read, the acceptance criteria (build + test
green), and the commit message style. Subagents inherit CLAUDE.md so they
follow the same rules.

## Roadmap discipline

acdream's plan lives in two files committed to the repo:

- **`docs/plans/2026-04-11-roadmap.md`** — the strategic roadmap. Single
  source of truth for what's shipped, what's next, and the agreed order.
  When you're about to pick up new work, read this first. When you ship a
  phase or sub-step, move it from "ahead" to "shipped" in the same commit
  that lands the work (or the very next commit).

- **`docs/superpowers/specs/*.md`** — per-phase detailed implementation
  specs. Each active phase has one. When you're about to write code for a
  named phase, read its spec, follow its component boundaries, and match its
  acceptance criteria. Do not drift from the spec without explicit user
  approval.

**Rules:**

1. Before starting a new phase or sub-piece, re-read the roadmap and the
   relevant spec. State which phase you're on in the first action you take.

2. When reality and the plan diverge — the user observes a bug that doesn't
   fit any existing phase, a technical discovery makes a phase description
   wrong, a sub-piece turns out to be larger than expected — **pause and
   brainstorm** with the `superpowers:brainstorming` skill before writing
   code. Update the roadmap in the same session.

3. When shipping a phase, update the roadmap's "shipped" table and commit
   the update in the same commit as (or immediately after) the
   implementation commit.

4. Do not invent new phase numbers / letters on the fly. If you need a new
   phase, add it to the roadmap first with the user, then reference it by
   its assigned identifier. "Phase 11" and "Phase 9.3" conjured
   mid-sentence are process smells — they mean the plan got out of sync
   with the work.

5. If a single session ends up shipping work that spans multiple roadmap
   phases, that's fine, but each commit message should name the phase it
   belongs to (e.g. `feat(core): Phase A.1 — streaming region`).

The roadmap is not sacred — it changes. It IS the source of truth at any
given moment. When it's wrong, fix it. When it's right, follow it.

## Reference repos: check ALL FOUR, not just one

When researching a protocol detail, dat format, rendering algorithm, or
any "how does AC do X" question, **check all four of the vendored
references in `references/`** before committing to an approach. Do not
settle on the first hit and move on — cross-reference at least two of
these, ideally all four:

- **`references/ACE/`** — ACEmulator server. Authority on the wire
  protocol (packet framing, ISAAC, game message opcodes, serialization
  order). The things a server has to know to parse and produce bytes.
- **`references/ACViewer/`** — MonoGame-based dat viewer that actually
  renders characters + world. Authority on the client-side visual
  pipeline: ObjDesc application, palette overlays, texture decoding
  for the palette-indexed formats. See
  `ACViewer/Render/TextureCache.cs::IndexToColor` for the canonical
  subpalette overlay algorithm.
- **`references/WorldBuilder/`** — C# + Silk.NET dat editor. Exact-stack
  match to acdream for rendering approaches: terrain blending, texture
  atlases, shader patterns. Most useful for "how do I do this GL thing
  with Silk.NET on net10 idiomatically?" Less useful for protocol or
  character appearance (dat editor, not game client).
- **`references/Chorizite.ACProtocol/`** — clean-room C# protocol
  library generated from a protocol XML description. Useful sanity check
  on field order, packed-dword conventions, type-prefix handling. The
  generated Types/*.cs files have accurate field comments (e.g. "If
  it is 0, it defaults to 256*8") that ACE's server-side code doesn't.
- **`references/holtburger/`** — Rust AC client crate. Cross-references
  handshake quirks, race delays, and per-message encoding decisions
  that ACE doesn't document because it's server-side.

Pattern: when you encounter an unknown behavior, grep all four for the
relevant term, read each hit, and compose a multi-source understanding
BEFORE writing acdream code. A single reference can be misleading; the
intersection of all four is almost always the truth. The user has
repeatedly had to remind me about this when I narrowly searched one ref
and missed obvious answers in another.