git:20261031.7e4d9ab to git:20261101.f934ce3

---

name: flow

description: "Run a medium or large request on the main thread: parallel research, interview, build in slices, oracle review."

when_to_use: "Use before building anything that touches several files, an unfamiliar area or an open behaviour choice; not for a one-file change or an explicit /ac:plan."

---

# ac:flow

The default build flow for a request the working rules sized M or L. You stay on the main thread: research runs on cheap subagents, the user settles what only they can, you build (L: through tiered workers), and one `ac:oracle` reviews the result. No plan file is written. `/ac:plan` and `/ac:coordinate` start only when the user asks for them.

## Standing rules

These hold for the whole run and sit before the procedure so a compaction keeps them.

- Sizes are the working rules' S, M and L. Between two sizes take the larger; when research changes the picture, resize and say so in one line.

- Spend. Research runs on `ac:explore` (this repository) and `ac:librarian` (anything external), building on `ac:plan-worker-*`, review on `ac:oracle`. Never `general-purpose`: it inherits this session's model and effort, which makes it the costliest way to run a slice.

- One message per fan-out. Every independent Agent call of a phase goes out together. Each brief names one angle; two angles are two briefs.

- Interactive sessions run every subagent in the background. After a fan-out, end the turn with a one-line status and continue on the notification. Do not poll, sleep, or read an output file.

- A subagent report is a claim. Open what it cites before it changes a decision.

- The review in phase 6 is the only reviewer. Do not spawn an agent to re-check your own work.

- Ceiling. More than six slices, or work that will not finish in this sitting: stop before phase 4 and ask once with `AskUserQuestion` whether to continue here or to hand the work to `/ac:plan` or `/ac:coordinate`. Do not invoke either yourself.

## 1. Size and success check

State both in one line: "M: <what changes>; done when <checkable condition>". The success check is what phase 5 and 6 hold you to.

## 2. Research (M and L)

M: one to three briefs in total. L: three to five `ac:explore` and one or two `ac:librarian`. Skip an angle one or two reads would settle, and skip the phase when the request names every file and line.

Brief shape, one block per angle:

```

CONTEXT: why this research, one or two sentences; cite the file or symbol you started from

GOAL: the specific question to answer

DEPTH: quick | medium | thorough

BUDGET: explore: a pass count. librarian: a number of web searches, five is the working ceiling

DOWNSTREAM: how you will use the result

REQUEST: what to return, the format, what to skip

```

`DEPTH` and `BUDGET` are required: an agent cannot apply a depth you did not send, and a blank field returns the thin default pass. For `ac:explore` also pass the Agent tool's `effort` from `DEPTH` (`quick` is `"low"`, `medium` is `"medium"`, `thorough` is `"high"`), unless `CLAUDE_CODE_EFFORT_LEVEL` is set. `ac:librarian` takes none. `ac:librarian` does not read CLAUDE.md, so anything the user told you to leave out of research goes into its brief.

## 3. Interview

Answer from the code and the research first; ask only a preference, a priority, a tradeoff or an outward action.

- M: only the decisions that block the build, in one `AskUserQuestion` call of up to three questions.

- L: walk the decisions that shape the result in rounds of up to three questions, until each has an answer or an accepted default. Record the defaults you assumed.

- Each option carries the concrete artifact (the snippet, path, value or consequence), your recommendation first, in the user's language.

- A decision that blocks nothing: take your recommendation, say so, carry on.

## 4. Build

M: implement it yourself, in the order that keeps each step verifiable.

L: write the slice table in your reply; it is also the progress list. Mark a row as it lands.

| # | Goal | Files | After | Tier | Done when |

|---|------|-------|-------|------|-----------|

- Files are disjoint across slices that run together. Two slices that touch one file are one slice, or run in order.

- Tier: the lowest that fits the slice, from the table in `${CLAUDE_SKILL_DIR}/references/worker-brief.md`.

- Dispatch each ready wave (slices whose `After` is met, files disjoint) as `ac:plan-worker-<tier>` calls, at most three at once, with the brief from `${CLAUDE_SKILL_DIR}/references/worker-brief.md`. Fill every section; a worker never opens anything you did not put in the brief.

- After a wave: compare `git diff --stat` with the slice file lists. A hunk no worker claimed, or a file outside a list, is yours to fix or revert. Then run, once for the wave and in parallel, the per-file checks on the wave's touched files, their related tests and one project-wide static analysis; never the full suite here (`${CLAUDE_PLUGIN_ROOT}/references/verification.md`).

- Fix remediation yourself. Re-spawn a worker only for a `[BRIEFING GAP]` (repair the brief) or a tier mismatch (one tier up).

## 5. Verify

Hold the result to the success check from phase 1: the changed files clean by their CLI analyzer (an LSP diagnostic is a hint that can be stale; confirm it before you fix or dismiss it), the tests covering the change green (if nothing covers it, say so), and anything user-visible exercised the way a person would. Stop what you started.

## 6. Review

Start the full test suite and the repo-wide lint with `run_in_background: true`, whether or not an oracle runs; both must be green before you report, and a failure there is a finding like the oracle's. One `ac:oracle`, in the same message, when the change crosses more than one file or is hard to reverse; a single-file M skips it. Send the diff and the claims it rests on: the success check, the interview decisions, the research sources. Fix what it confirms and say which findings you left and why.

## 7. Report

## References

| File | Read when |

|---|---|

| `${CLAUDE_SKILL_DIR}/references/worker-brief.md` | Phase 4, for every worker spawn and the tier table |