flow-next-capture

# /flow-next:capture — agent-native conversation → spec

A free-form discussion (or a `/flow-next:prospect` survivor) frequently produces enough material for a complete spec, but stops short of the formal `flowctl spec create` + `spec set-plan` heredoc documented in `CLAUDE.md`. Without an explicit synthesis step, that context decays — the next session loses the conversation, the spec never lands, and the user re-explains the same idea to `/flow-next:plan`.

This skill IS the synthesis. The host agent (Claude Code / Codex / Droid) extracts the recent user turns, drafts a CLAUDE.md-shaped spec with **per-line source tags** (`[user]` / `[paraphrase]` / `[inferred]` / `[strategy:<track>]`), **prints the full draft as ordinary markdown then issues a short approval ask** (print-then-ask — never embed multi-paragraph drafts in `AskUserQuestion` bodies), and only then writes the spec via existing flowctl plumbing. There is no Python synthesizer, no codex / copilot subprocess, no fast-model classifier. The host agent is already an LLM and does the work directly.

flowctl provides thin spec plumbing (`spec create`, `spec set-plan`, optional `spec set-branch`, `memory search` for duplicate detection) plus the chart handoff callback (`chart link-spec`) after a successful chart-briefing capture. Capture never writes chart files and never mutates a chart's `ready` flag; chart never writes `.flow/specs`.

### Routing boundary (fn-135 / guide matrix)

Clear meaningful ideas and finished chart briefings route **here** - to capture (or direct spec authoring). Capture does **not** manufacture a chart for clear work. When intent and boundaries are already stateable, skip chart (`signal absent`). After a structured brief lands, narrow or skip interview only once read-back proves no material gaps - never pre-skip interview on hope. Unsure: `/flow-next:guide`.

**Read [workflow.md](workflow.md) for the full phase-by-phase execution. Read [phases.md](phases.md) for the source-tag taxonomy and confidence tiers.** Path-specific machinery lives in `references/*.md`, loaded only when the gate at its branch point fires — a run that never takes a branch never pays for it.

## Preamble

**CRITICAL: flowctl is BUNDLED — NOT installed globally.** `which flowctl` will fail (expected). Define once; subsequent blocks (here and in `workflow.md` / `phases.md`) use `$FLOWCTL`:

```bash
FLOWCTL="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/flowctl"
[ -x "$FLOWCTL" ] || FLOWCTL="<plugin-root>/scripts/flowctl"   # <plugin-root> = the directory two levels above this skill's SKILL.md file (the harness gave you that file's absolute path when the skill loaded); substitute it literally
[ -x "$FLOWCTL" ] || FLOWCTL=".flow/bin/flowctl"
```

**Inline skill (no `context: fork`)** — `AskUserQuestion` must stay reachable across phases. Subagents can't call blocking question tools (Claude Code issues #12890, #34592). Phase 0 (duplicate detection) and Phase 4 (read-back loop) both require user choice in interactive mode. (sync-codex.sh rewrites this to a plain-text numbered prompt in the Codex mirror.)

## Mode Detection

Parse `$ARGUMENTS` for the literal token `mode:autofix` and the flags `--rewrite <spec-id>`, `--from-compacted-ok`, `--yes`, `--override-strategy`, `--no-plan`. Strip recognized tokens; whatever remains is treated as freeform context (ignored — the conversation is the input, not `$ARGUMENTS`).

```bash
RAW_ARGS="$ARGUMENTS"
MODE="interactive"
REWRITE_TARGET=""
FROM_COMPACTED_OK=0
COMMIT_YES=0
OVERRIDE_STRATEGY=0

# Mode token
if [[ "$RAW_ARGS" == *"mode:autofix"* ]]; then
  MODE="autofix"
  RAW_ARGS="${RAW_ARGS//mode:autofix/}"
fi

# --rewrite <id>
if [[ "$RAW_ARGS" =~ --rewrite[[:space:]]+([^[:space:]]+) ]]; then
  REWRITE_TARGET="${BASH_REMATCH[1]}"
  RAW_ARGS="${RAW_ARGS//--rewrite ${REWRITE_TARGET}/}"
fi

# --from-compacted-ok
if [[ "$RAW_ARGS" == *"--from-compacted-ok"* ]]; then
  FROM_COMPACTED_OK=1
  RAW_ARGS="${RAW_ARGS//--from-compacted-ok/}"
fi

# --yes (autofix commit gate)
if [[ "$RAW_ARGS" == *"--yes"* ]]; then
  COMMIT_YES=1
  RAW_ARGS="${RAW_ARGS//--yes/}"
fi

# --override-strategy (Phase 5.0 strategy-contradiction override)
if [[ "$RAW_ARGS" == *"--override-strategy"* ]]; then
  OVERRIDE_STRATEGY=1
  RAW_ARGS="${RAW_ARGS//--override-strategy/}"
fi

# --no-plan (fn-214, R5: explicit opt-in to set the spec-level no_plan field
# in §5.9b after the spec write — NEVER inferred from conversation content;
# autofix sets the field only through this flag). EXACT-token match, not a
# substring test: durable state must not be set by lookalikes ("--no-planning",
# "--no-plan=false") — those stay in the freeform remainder untouched.
NO_PLAN_OPT=0
CLEANED_ARGS=""
for TOK in $RAW_ARGS; do
  if [ "$TOK" = "--no-plan" ]; then
    NO_PLAN_OPT=1
  else
    CLEANED_ARGS="$CLEANED_ARGS $TOK"
  fi
done
RAW_ARGS="$CLEANED_ARGS"

if [ "$MODE" = "autofix" ]; then
  echo "GATE ACTIVE — STOP. Read references/autofix-mode.md before continuing."
fi   # default branch: bare no-op — NO link, NO read path
```

| Mode | When | Behavior |
|------|------|----------|
| **Interactive** (default) | User is at the terminal | Phase 0 asks on duplicate detection; Phase 3 asks on must-ask ambiguities; Phase 4 print-then-ask read-back (full draft as ordinary markdown, then short blocking-question tool) — write only on `approve` |
| **Autofix** (`mode:autofix`) | Batch usage from another skill / scripted invocation | No user questions; every "ask" branch becomes exit 2; Phase 4 Writes the draft once and requires `--yes` to reach the `.flow/` write |

When the sentinel above prints, read [references/autofix-mode.md](references/autofix-mode.md) before Phase 0 — it owns the per-phase autofix rules (Phase 0 hard-errors, Phase 3 exits, §4.4 read-back substitute, split / glossary / readiness behavior). On the default interactive path, read nothing.

## Ralph-block (R13) — runs first, before everything else

`/flow-next:capture` requires conversatio