@garygentry/feature-forge 0.2.1 → 0.2.3

package/adapters/cursor/scripts/forge-session.py

@@ -0,0 +1,491 @@
+#!/usr/bin/env python3
+"""Session-aware navigation helpers for the feature-forge pipeline navigator.
+
+Two read-only subcommands that drive the usability features of the `/forge`
+root navigator:
+
+    python3 forge-session.py rank-features [--specs-dir DIR] [--json]
+    python3 forge-session.py context-usage [--config FILE] [--window N] \
+        [--threshold F] [--json]
+
+`rank-features` scans the specs tree for feature-shaped directories (those that
+directly contain a `.pipeline-state.json`, in both the flat
+`{specsDir}/{feature}/` and nested `{specsDir}/{epic}/{feature}/` layouts) and
+reports the **active** ones ordered by `updatedAt` descending, so the navigator
+can offer the most-recently-touched feature as the recency default. Each row
+carries the next actionable stage + its slash command, derived from the single
+ordered stage map below.
+
+`context-usage` reads the live Claude Code session transcript (the most-recently
+modified `*.jsonl` under `~/.claude/projects/<cwd-slug>/`), sums the last
+assistant message's token usage, and compares it to the context window so the
+navigator can recommend a clean session before the next stage. It is best-effort
+and degrades gracefully: when no transcript or usage is found (a non-Claude host,
+or a fresh session) it reports `{"available": false}` and still exits 0, so the
+caller simply omits the context advice.
+
+3.10 baseline, Google-style docstrings, full type annotations, stdlib only —
+matching the conventions of `scripts/epic-manifest.py`.
+
+Exit codes:
+    0 = ok (including an empty feature list or unavailable context usage)
+    2 = usage error or unreadable I/O
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import sys
+from datetime import datetime
+from pathlib import Path
+from typing import Final, TypedDict
+
+
+# --------------------------------------------------------------------------- #
+# Constants
+# --------------------------------------------------------------------------- #
+
+#: A directory is "feature-shaped" iff it directly contains this file.
+PIPELINE_STATE_FILENAME: Final = ".pipeline-state.json"
+#: Epic roots hold this (and no .pipeline-state.json) — never a feature.
+MANIFEST_FILENAME: Final = "epic-manifest.json"
+
+#: The ordered production stages. This is the ONE place stage order lives.
+PRODUCTION_STAGES: Final[tuple[str, ...]] = (
+    "forge-1-prd",
+    "forge-2-tech",
+    "forge-3-specs",
+    "forge-4-backlog",
+    "forge-5-loop",
+    "forge-6-docs",
+)
+
+#: Production stage -> the verify token its findings file uses, and the
+#: `forge-verify-<token>` key its state lives under. forge-6-docs has no verify.
+VERIFY_TOKEN_BY_STAGE: Final[dict[str, str]] = {
+    "forge-1-prd": "prd",
+    "forge-2-tech": "tech",
+    "forge-3-specs": "specs",
+    "forge-4-backlog": "backlog",
+    "forge-5-loop": "impl",
+}
+
+#: A production stage status that counts as "done" for next-stage selection.
+_DONE_STATUS: Final = "complete"
+#: Verify statuses that count as "resolved" (no outstanding verify needed).
+_VERIFY_RESOLVED: Final = frozenset({"passed", "findings-applied", "skipped"})
+
+#: Default context window when the model can't be inferred and config is silent.
+_DEFAULT_WINDOW: Final = 200_000
+#: Window for 1M-context models (model id carries a `[1m]` / `-1m` marker).
+_WIDE_WINDOW: Final = 1_000_000
+#: Default fraction of the window past which a clean session is recommended.
+_DEFAULT_THRESHOLD: Final = 0.7
+
+
+# --------------------------------------------------------------------------- #
+# Types
+# --------------------------------------------------------------------------- #
+
+
+class FeatureRow(TypedDict):
+    """One active feature, ranked by recency, with its next actionable step."""
+
+    name: str
+    epic: str | None
+    currentStage: str
+    branch: str | None
+    updatedAt: str | None
+    complete: bool
+    nextStage: str | None
+    nextCommand: str | None
+    verifyPending: bool
+    verifyCommand: str | None
+
+
+class UsageError(Exception):
+    """A usage or I/O failure that must exit 2."""
+
+
+# --------------------------------------------------------------------------- #
+# Feature scanning & ranking
+# --------------------------------------------------------------------------- #
+
+
+def _read_state(state_path: Path) -> dict:
+    """Read a `.pipeline-state.json`, tolerating missing/corrupt files.
+
+    A missing, unreadable, or unparseable state downgrades to ``{}`` rather than
+    crashing the scan — the navigator simply treats that feature as not-started.
+    """
+    try:
+        parsed = json.loads(state_path.read_text(encoding="utf-8"))
+    except (OSError, json.JSONDecodeError):
+        return {}
+    return parsed if isinstance(parsed, dict) else {}
+
+
+def _scan_features(specs_dir: Path) -> list[tuple[str, str | None, dict]]:
+    """Find every feature-shaped dir under the specs tree (flat + nested).
+
+    Descends exactly one level below each top-level dir (never deeper), matching
+    ``epic-manifest.py``'s feature-shaped-dir bound.
+
+    Args:
+        specs_dir: The configured specs directory.
+
+    Returns:
+        A list of ``(feature_name, epic_name_or_None, state_dict)`` tuples. The
+        epic name is the parent dir name for a nested member, ``None`` for a flat
+        feature.
+    """
+    if not specs_dir.is_dir():
+        return []
+    out: list[tuple[str, str | None, dict]] = []
+    for top in sorted(p for p in specs_dir.iterdir() if p.is_dir()):
+        flat_state = top / PIPELINE_STATE_FILENAME
+        if flat_state.is_file():
+            out.append((top.name, None, _read_state(flat_state)))
+        # Descend one level for nested epic members (skip the epic root itself).
+        for child in sorted(p for p in top.iterdir() if p.is_dir()):
+            nested_state = child / PIPELINE_STATE_FILENAME
+            if nested_state.is_file():
+                out.append((child.name, top.name, _read_state(nested_state)))
+    return out
+
+
+def _stage_status(state: dict, stage: str) -> str | None:
+    """Return the recorded status of a stage, or None if absent."""
+    stages = state.get("stages")
+    if not isinstance(stages, dict):
+        return None
+    entry = stages.get(stage)
+    if not isinstance(entry, dict):
+        return None
+    status = entry.get("status")
+    return status if isinstance(status, str) else None
+
+
+def next_stage(state: dict) -> str | None:
+    """Return the first production stage that is not yet complete (the next step).
+
+    Walks ``PRODUCTION_STAGES`` in order and returns the first whose recorded
+    status is not ``complete`` (a missing/pending/in-progress/stale stage all
+    count as "not done"). Returns ``None`` when every production stage is
+    complete (nothing left to run).
+    """
+    for stage in PRODUCTION_STAGES:
+        if _stage_status(state, stage) != _DONE_STATUS:
+            return stage
+    return None
+
+
+def pending_verify(state: dict) -> str | None:
+    """Return the production stage whose verify is outstanding, if any.
+
+    The most recently completed production stage whose corresponding
+    ``forge-verify-*`` is neither resolved (passed/findings-applied/skipped) nor
+    already run. Surfaced so the navigator can offer "verify before continuing"
+    as an alternative to advancing. Returns ``None`` when nothing needs verify.
+    """
+    for stage in reversed(PRODUCTION_STAGES):
+        if _stage_status(state, stage) != _DONE_STATUS:
+            continue
+        token = VERIFY_TOKEN_BY_STAGE.get(stage)
+        if token is None:
+            continue  # forge-6-docs has no verify step
+        verify_status = _stage_status(state, f"forge-verify-{token}")
+        if verify_status not in _VERIFY_RESOLVED:
+            return stage
+        return None  # most-recent complete stage is already verified
+    return None
+
+
+def _parse_ts(value: str | None) -> datetime | None:
+    """Parse an ISO-8601 timestamp (tolerating a trailing 'Z'), else None."""
+    if not isinstance(value, str):
+        return None
+    try:
+        return datetime.fromisoformat(value.replace("Z", "+00:00"))
+    except ValueError:
+        return None
+
+
+def build_rows(specs_dir: Path) -> list[FeatureRow]:
+    """Build the recency-ranked active-feature rows (the rank-features payload).
+
+    Active features (``pipelineStatus == "active"``, the default when absent) are
+    sorted by ``updatedAt`` descending — most recently touched first — so the
+    navigator's recency default is row 0.
+    """
+    rows: list[FeatureRow] = []
+    for name, epic, state in _scan_features(specs_dir):
+        status = state.get("pipelineStatus", "active")
+        if status != "active":
+            continue
+        nxt = next_stage(state)
+        verify_stage = pending_verify(state)
+        branch = state.get("branch")
+        updated = state.get("updatedAt")
+        rows.append({
+            "name": name,
+            "epic": epic,
+            "currentStage": state.get("currentStage") or (nxt or "complete"),
+            "branch": branch if isinstance(branch, str) else None,
+            "updatedAt": updated if isinstance(updated, str) else None,
+            "complete": nxt is None,
+            "nextStage": nxt,
+            "nextCommand": f"/feature-forge:{nxt} {name}" if nxt else None,
+            "verifyPending": verify_stage is not None,
+            "verifyCommand": f"/feature-forge:forge-verify {name}" if verify_stage else None,
+        })
+    # Sort by updatedAt desc; rows without a parseable timestamp sort last.
+    rows.sort(
+        key=lambda r: (_parse_ts(r["updatedAt"]) or datetime.min.replace(tzinfo=None)),
+        reverse=True,
+    )
+    return rows
+
+
+def _counts(specs_dir: Path) -> dict[str, int]:
+    """Tally active/paused/abandoned pipelines across the specs tree."""
+    tally = {"active": 0, "paused": 0, "abandoned": 0}
+    for _name, _epic, state in _scan_features(specs_dir):
+        status = state.get("pipelineStatus", "active")
+        if status in tally:
+            tally[status] += 1
+    return tally
+
+
+# --------------------------------------------------------------------------- #
+# Context-window usage
+# --------------------------------------------------------------------------- #
+
+
+def _cwd_slug(cwd: Path) -> str:
+    """Map a working directory to its Claude Code project-dir slug.
+
+    Claude Code names the per-project transcript dir by replacing path
+    separators (and dots) in the absolute cwd with hyphens, e.g.
+    ``/home/u/proj`` -> ``-home-u-proj``.
+    """
+    return str(cwd.resolve()).replace("/", "-").replace(".", "-")
+
+
+def _latest_transcript(cwd: Path) -> Path | None:
+    """Return the most-recently-modified transcript JSONL for this cwd, if any."""
+    project_dir = Path.home() / ".claude" / "projects" / _cwd_slug(cwd)
+    if not project_dir.is_dir():
+        return None
+    transcripts = [p for p in project_dir.glob("*.jsonl") if p.is_file()]
+    if not transcripts:
+        return None
+    return max(transcripts, key=lambda p: p.stat().st_mtime)
+
+
+def _last_usage(transcript: Path) -> tuple[int, str | None] | None:
+    """Scan a transcript from the end for the last `usage` record.
+
+    Returns ``(token_total, model_id)`` where the total sums
+    ``input_tokens + cache_creation_input_tokens + cache_read_input_tokens +
+    output_tokens`` of the most recent message carrying a usage object — i.e. the
+    current context occupancy. Returns ``None`` if no usable record is found.
+    """
+    try:
+        lines = transcript.read_text(encoding="utf-8").splitlines()
+    except OSError:
+        return None
+    for line in reversed(lines):
+        line = line.strip()
+        if not line or '"usage"' not in line:
+            continue
+        try:
+            record = json.loads(line)
+        except json.JSONDecodeError:
+            continue
+        message = record.get("message")
+        usage = message.get("usage") if isinstance(message, dict) else record.get("usage")
+        if not isinstance(usage, dict):
+            continue
+        total = (
+            int(usage.get("input_tokens", 0) or 0)
+            + int(usage.get("cache_creation_input_tokens", 0) or 0)
+            + int(usage.get("cache_read_input_tokens", 0) or 0)
+            + int(usage.get("output_tokens", 0) or 0)
+        )
+        if total <= 0:
+            continue
+        model = message.get("model") if isinstance(message, dict) else record.get("model")
+        return total, (model if isinstance(model, str) else None)
+    return None
+
+
+def _infer_window(model: str | None) -> int:
+    """Infer the context window from a model id (1M-context markers -> wide)."""
+    if model and ("[1m]" in model.lower() or "-1m" in model.lower()):
+        return _WIDE_WINDOW
+    return _DEFAULT_WINDOW
+
+
+def _config_value(config_path: Path, key: str):
+    """Read a single key from forge.config.json, or None if absent/unreadable."""
+    try:
+        config = json.loads(config_path.read_text(encoding="utf-8"))
+    except (OSError, json.JSONDecodeError):
+        return None
+    return config.get(key) if isinstance(config, dict) else None
+
+
+def context_usage(
+    config_path: Path,
+    window_override: int | None,
+    threshold_override: float | None,
+) -> dict:
+    """Compute live context-window occupancy for the current session.
+
+    Window precedence: ``--window`` > config ``contextWindowTokens`` > inferred
+    from the transcript's model id > ``_DEFAULT_WINDOW``. When inferring (no
+    override, no config) and the observed token total already exceeds the default
+    window, the window is auto-bumped to ``_WIDE_WINDOW`` — observed tokens above
+    200k prove a wider (1M-beta) window is active, so this corrects the reading
+    without ever under-reporting a genuine 200k session. Threshold precedence:
+    ``--threshold`` > config ``contextWarnThreshold`` > ``_DEFAULT_THRESHOLD``.
+
+    Returns a dict with ``available: True`` and ``{tokens, windowTokens, pct,
+    overThreshold, recommendation, model}`` when usage is found, or
+    ``{available: False, reason}`` otherwise. Never raises for a missing
+    transcript — that is the expected non-Claude / fresh-session path.
+    """
+    threshold = threshold_override
+    if threshold is None:
+        cfg_threshold = _config_value(config_path, "contextWarnThreshold")
+        threshold = (
+            float(cfg_threshold)
+            if isinstance(cfg_threshold, (int, float))
+            else _DEFAULT_THRESHOLD
+        )
+
+    transcript = _latest_transcript(Path.cwd())
+    if transcript is None:
+        return {"available": False, "reason": "no session transcript found"}
+    found = _last_usage(transcript)
+    if found is None:
+        return {"available": False, "reason": "no usage record in transcript"}
+    tokens, model = found
+
+    window = window_override
+    if window is None or window <= 0:
+        cfg_window = _config_value(config_path, "contextWindowTokens")
+        if isinstance(cfg_window, int) and cfg_window > 0:
+            window = cfg_window
+        else:
+            # Inferring (no override, no config). Start from the model marker /
+            # conservative default, then auto-bump: observed tokens above the
+            # default window PROVE a wider window is active (a 200k session can
+            # never exceed 200k), so widen to 1M rather than report a nonsensical
+            # >100%. Never under-reports a real 200k session, which can't trip it.
+            window = _infer_window(model)
+            if tokens > window:
+                window = _WIDE_WINDOW
+
+    pct = round(tokens / window, 4)
+    over = pct >= threshold
+    if over:
+        recommendation = "clean-session"
+    else:
+        recommendation = "continue"
+    return {
+        "available": True,
+        "tokens": tokens,
+        "windowTokens": window,
+        "pct": pct,
+        "threshold": threshold,
+        "overThreshold": over,
+        "recommendation": recommendation,
+        "model": model,
+    }
+
+
+# --------------------------------------------------------------------------- #
+# CLI dispatch
+# --------------------------------------------------------------------------- #
+
+
+def _print_rank_table(rows: list[FeatureRow], counts: dict[str, int]) -> None:
+    """Print a human-readable recency-ranked feature list."""
+    print(
+        f"Active: {counts['active']}  "
+        f"(paused: {counts['paused']}, abandoned: {counts['abandoned']})"
+    )
+    if not rows:
+        print("  (no active feature pipelines)")
+        return
+    for idx, row in enumerate(rows):
+        marker = "→" if idx == 0 else " "
+        label = row["name"] + (f" [{row['epic']}]" if row["epic"] else "")
+        nxt = row["nextCommand"] or "complete"
+        print(f"  {marker} {label}: {row['currentStage']} — next: {nxt}")
+        if row["verifyPending"]:
+            print(f"      (verify available: {row['verifyCommand']})")
+
+
+def _print_context(usage: dict) -> None:
+    """Print a one-line human-readable context-usage summary."""
+    if not usage.get("available"):
+        print(f"context usage: unavailable ({usage.get('reason', 'unknown')})")
+        return
+    pct = round(usage["pct"] * 100, 1)
+    flag = " — over threshold, clean session recommended" if usage["overThreshold"] else ""
+    print(
+        f"context: {usage['tokens']:,} / {usage['windowTokens']:,} tokens "
+        f"(~{pct}%){flag}"
+    )
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(prog="forge-session.py", description=__doc__)
+    sub = parser.add_subparsers(dest="cmd", required=True)
+
+    p_rank = sub.add_parser("rank-features", help="Rank active features by recency")
+    p_rank.add_argument("--specs-dir", default="./specs", help="Specs directory")
+    p_rank.add_argument("--json", action="store_true", dest="json_output")
+
+    p_ctx = sub.add_parser("context-usage", help="Report live context-window usage")
+    p_ctx.add_argument("--config", default="./forge.config.json", help="forge.config.json path")
+    p_ctx.add_argument("--window", type=int, default=None, help="Override context window size")
+    p_ctx.add_argument("--threshold", type=float, default=None, help="Override warn fraction (0-1)")
+    p_ctx.add_argument("--json", action="store_true", dest="json_output")
+
+    args = parser.parse_args()
+
+    try:
+        if args.cmd == "rank-features":
+            specs_dir = Path(args.specs_dir)
+            rows = build_rows(specs_dir)
+            counts = _counts(specs_dir)
+            if args.json_output:
+                print(json.dumps({"active": rows, "counts": counts}, indent=2, ensure_ascii=False))
+            else:
+                _print_rank_table(rows, counts)
+            return 0
+
+        if args.cmd == "context-usage":
+            usage = context_usage(Path(args.config), args.window, args.threshold)
+            if args.json_output:
+                print(json.dumps(usage, indent=2, ensure_ascii=False))
+            else:
+                _print_context(usage)
+            return 0
+
+        raise UsageError(f"unknown command: {args.cmd}")
+    except UsageError as exc:
+        print(f"Error: {exc}", file=sys.stderr)
+        return 2
+    except OSError as exc:
+        print(f"Error: {exc}", file=sys.stderr)
+        return 2
+
+
+if __name__ == "__main__":
+    sys.exit(main())

package/adapters/cursor/skills/forge/forge.mdc

@@ -35,7 +35,14 @@ python3 "$R/scripts/epic-manifest.py" render-status "{epic}" --specs-dir "{specs
    ```
    and show one rollup line: `{epic} — {complete}/{total} complete, next: {nextCommand}`.
 2. **Standalone features below.** Scan the remaining `{specsDir}/*/` that directly contain a `.pipeline-state.json` **without** an `epic` back-pointer. A nested member's `.pipeline-state.json` is **attributed to its epic (Tier 1), never listed as a standalone feature**.
-   - Within this standalone tier the existing logic still applies: if exactly one active (non-complete) standalone pipeline exists, show its dashboard; if multiple exist, list them with a one-line summary each and use the host's question mechanism to ask which to focus on.
+   - **Rank by recency.** Run the recency ranker so the most-recently-touched active feature is the default — the user rarely has to type a name (especially on mobile after a `/clear`):
+     ```bash
+R="$(for d in "$HOME"/.claude/skills/feature-forge "$HOME"/.claude/plugins/*/feature-forge "$HOME"/.agents/skills/feature-forge ./.agents/skills/feature-forge; do [ -x "$d/scripts/forge-root.sh" ] && exec "$d/scripts/forge-root.sh"; done)"
+[ -n "$R" ] || { echo "feature-forge: cannot locate plugin root" >&2; exit 1; }
+python3 "$R/scripts/forge-session.py" rank-features --specs-dir "{specsDir}" --json
+     ```
+     This returns `{active: [...], counts: {...}}` with active features sorted by `updatedAt` **descending** (row 0 is the most recent). Each row carries `currentStage`, `nextStage`, `nextCommand`, `verifyPending`, and `verifyCommand` (the single source of stage order). The `active` list excludes nested epic members surfaced in Tier 1 — but the ranker scans them too, so ignore rows whose `epic` is non-null here (they belong to the epic rollup).
+   - **Pick the feature:** if exactly one active standalone pipeline exists, show its dashboard. If multiple exist, use the host's question mechanism — **list the most-recently-updated first, labeled `(recommended)`**, each option's description showing its `currentStage` and a relative age ("updated 2h ago"). Always include a free-form escape ("A different feature / something else") so the user is never boxed in. Then render the chosen feature's dashboard.
 
 If no epics and no standalone features exist, say: "No active feature pipelines found. Start one with `/feature-forge:forge-1-prd <feature-name>` or group several with `/feature-forge:forge-0-epic <epic-name>`."
 
@@ -78,6 +85,35 @@ Use these status indicators:
 - ⏭️ = verification skipped (user chose to proceed without verifying)
 - ⚠️ = stale (built against an older version of an upstream artifact)
 
+### 3b. Drive to the Next Stage
+
+After rendering a **per-feature** dashboard for an **active** pipeline (skip this for paused/abandoned pipelines and for the Epic Dashboard), don't stop at a text suggestion — actively offer to start the next stage. This removes the copy-paste-after-`/clear` chore that makes long, multi-stage runs painful (especially on mobile).
+
+**1. Read the next step.** From the `rank-features --json` output (above), find this feature's row and read its `nextStage`, `nextCommand`, `verifyPending`, and `verifyCommand`. If the feature is not in the `active` list (paused/abandoned), or `nextStage` is `null` (every production stage complete), skip the drive prompt — instead congratulate the user and, if `forge-6-docs` has not run, offer it; otherwise note the pipeline is complete.
+
+**2. Check the context window.** Run the context-usage helper so you can advise whether to continue here or start the next stage in a fresh session:
+```bash
+R="$(for d in "$HOME"/.claude/skills/feature-forge "$HOME"/.claude/plugins/*/feature-forge "$HOME"/.agents/skills/feature-forge ./.agents/skills/feature-forge; do [ -x "$d/scripts/forge-root.sh" ] && exec "$d/scripts/forge-root.sh"; done)"
+[ -n "$R" ] || { echo "feature-forge: cannot locate plugin root" >&2; exit 1; }
+python3 "$R/scripts/forge-session.py" context-usage --json
+```
+- `{"available": true, ...}` → note `pct` (e.g. "context ~68% full") and `overThreshold`. Window/threshold come from `contextWindowTokens` / `contextWarnThreshold` in `forge.config.json` (the helper defaults to a 200k window and 0.7 threshold, and auto-bumps the assumed window to 1M once observed usage exceeds 200k; **on a 1M-context model set `contextWindowTokens: 1000000` so the percentage is accurate below 200k too** — 1M can't be detected from the transcript until usage crosses 200k).
+- `{"available": false, ...}` → omit context advice silently (non-Claude host, or a fresh session with no transcript). Never treat this as an error.
+
+**3. Offer the next step via the host's question mechanism.** Output the dashboard + a one-line context note as text, then ask (per the Decision Support protocol in `references/shared-conventions.md`). Options, in this order:
+- **Start `{nextStage}` now** — recommended **when context is healthy** (`overThreshold` false or context unavailable).
+- **Start in a clean session** — recommended-**first** instead **when `overThreshold` is true**. The work survives a clear because all state is on disk: instruct the user to `/clear`, then re-run `/feature-forge:forge {feature}` (or run `{nextCommand}` directly) in the fresh session. Note plainly that you cannot `/clear` for them.
+- **Verify `{stage}` first** — include **only when `verifyPending` is true**; selecting it runs `{verifyCommand}`.
+- **Pick a different stage** — free-form escape to any stage or other action.
+
+**4. Act on the choice.**
+- **Start now** → if `autoInvokeNextStage` is true (default) **and** the `Skill` tool is available, invoke the chosen stage **via the `Skill` tool** in this same session (e.g. `skill: "feature-forge:forge-3-specs"`, `args: "{feature}"`) — no retyping, no paste. If `autoInvokeNextStage` is false, or the `Skill` tool is unavailable (a non-Claude host), fall back to printing `{nextCommand}` prominently for the user to run.
+- **Clean session** → give the exact next command and the `/clear`-then-re-run instruction; do not invoke anything.
+- **Verify** → invoke `feature-forge:forge-verify` via the `Skill` tool (or print `{verifyCommand}` on a non-Claude host).
+- **Different stage** → honor the free-form request.
+
+This applies whether the feature was named explicitly (`/feature-forge:forge {feature}`) or resolved from the recency default.
+
 ### Epic Dashboard
 
 When the named argument is an epic (`{specsDir}/{name}/epic-manifest.json` exists), render the epic dashboard instead of a per-feature one. Run:
@@ -143,6 +179,12 @@ Support these sub-commands for pipeline lifecycle management:
 - `/feature-forge:forge pause {feature}` — Set `pipelineStatus` to `"paused"`. Do NOT modify `currentStage` or any stage statuses. The pipeline freezes exactly as-is. Show a confirmation.
 - `/feature-forge:forge resume {feature}` — Set `pipelineStatus` back to `"active"`. Calculate how long the feature was paused (from `updatedAt` to now). If paused for more than 24 hours, show a hint: "This feature was paused for {duration}. Session context may have been lost — consider re-running `/feature-forge:forge-{currentStage} {feature}` to rebuild context."
 - `/feature-forge:forge abandon {feature}` — Set `pipelineStatus` to `"abandoned"`. Use the host's question mechanism to confirm first, and state what's reversible: abandoning does not delete artifacts and can be undone with `/feature-forge:forge resume {feature}`, so the cost is low — but if the user really means "stop and discard," point out that `pause` is the better choice when they're only setting it aside. Offer **Abandon** · **Pause instead** · **Cancel**.
+- `/feature-forge:forge run [{feature}]` — **Opt-in auto-advance.** Drive the feature through consecutive stages in one session instead of confirming each boundary. This is a convenience wrapper over **3b. Drive to the Next Stage** — same stage order, same context gate — just looped:
+  1. Resolve the feature (if omitted, use the recency default from `rank-features`; if multiple are equally plausible, ask once via the host's question mechanism).
+  2. **Before each stage,** run `forge-session.py context-usage`. If `overThreshold` is true, **stop** and recommend a clean session (give the exact `{nextCommand}` and the `/clear`-then-re-run instruction) — never auto-`/clear`.
+  3. Otherwise invoke the next stage's skill via the `Skill` tool, let it run to its natural stopping point, then re-read state and continue from step 2.
+  4. **Stop conditions:** the next stage is an interview/decision point that calls the host's question mechanism (PRD and tech inherently pause for input — let them); `nextStage` is `null` (pipeline complete); context over threshold; or a stage signals it needs human input / is blocked. Always report where the loop stopped and why.
+  Per-stage confirmation (3b) remains the default — `run` is only used when the user explicitly asks to "run" / "drive" / "auto-advance" the pipeline. On a non-Claude host where the `Skill` tool is unavailable, fall back to printing the ordered list of commands to run.
 
 **Epic lifecycle.** When the argument names an **epic** (`{specsDir}/{name}/epic-manifest.json` exists), `pause` / `resume` / `abandon` operate on the epic manifest, not a `.pipeline-state.json`:
 

package/adapters/cursor/skills/forge-5-loop/forge-5-loop.mdc

@@ -197,7 +197,7 @@ Then commit this state write before launching (mandatory). The runner refuses to
 
 ### 3b. Launch Background Process
 
-Launch the loop **backgrounded** (the host's background-execution mechanism) so it survives session end and does not block the session, and prefer the machine-readable event stream (`loopRunner.eventStreamCommand`, default for rauf) redirected to a stable `events.ndjson` so the session can supervise it live; fall back to the plain `runCommand` (tailing the human log) when no `eventStreamCommand` is configured. The background task's exit notification is the single authoritative terminal signal (Step 4). Loop runs can take significant time (minutes to hours depending on backlog size). For the exact launch commands (incl. the `mkdir -p` state-dir guard) and the event-stream vs. log-fallback detail, read `references/runner-contract.md`.
+Launch the loop **backgrounded** (the host's background-execution mechanism) so it survives session end and does not block the session. For a runner that **persists its own structured event file** (the default — rauf writes `{stateDir}/events.ndjson` natively and rotates it per run), launch the **plain `runCommand`** with **no stdout redirect** and supervise the runner's **native** `events.ndjson` directly; do **not** redirect `--ndjson` into `{stateDir}` (it is redundant and collides with the runner's own writer — see `references/runner-contract.md`). Only a stdout-only runner (no native event file) uses `eventStreamCommand`, redirected to a file **outside** `{stateDir}`. The background task's exit notification is the single authoritative terminal signal (Step 4). Loop runs can take significant time (minutes to hours depending on backlog size). For the exact launch commands (incl. the `mkdir -p` state-dir guard) and the self-persisting vs. stdout-only detail, read `references/runner-contract.md`.
 
 ### 3c. Inform User
 
@@ -295,6 +295,7 @@ Update `{resolvedFeatureDir}/.pipeline-state.json`:
 
 ## Gotchas
 
+- **Plugin-root discovery (1b-epic helper) covers installed paths, not workspace-dev checkouts.** The `forge-root.sh` search in 1b-epic probes `~/.claude/skills/feature-forge`, `~/.claude/plugins/*/feature-forge`, and `./.agents/skills/feature-forge` — the locations of an **installed** plugin. A feature-forge **source checkout** (e.g. `~/workspace/feature-forge`) is not on that list, so the helper exits "cannot locate plugin root." That is expected in a dev environment, not a bug; run the epic-manifest script from the checkout directly (`python3 <checkout>/scripts/epic-manifest.py …`). Note the `~/.claude/plugins/*/feature-forge` glob can also print a zsh "no matches found" line when that dir is empty — harmless.
 - `{backlogDir}` is a **directory path**, not a file path. Pass `specs/auth`, not `specs/auth/backlog.json`.
 - rauf resolves `RAUF.md` with fallback: checks `{backlogDir}/.rauf/RAUF.md` first, then the project's `.rauf/RAUF.md`. As long as the runner is installed in the project, the prompt template will be found.
 - State files (state.json, {loopRunner.logFile}, etc.) are created at `{backlogDir}/{loopRunner.stateDir}/` — this is within the feature's spec directory and is expected. State is isolated per backlog dir, so concurrent features don't collide.