@runecraft/grimoire 1.0.0

package/skills/spec-driven/scripts/lessons.py

@@ -0,0 +1,370 @@
+#!/usr/bin/env python3
+"""
+lessons.py — deterministic bookkeeping for the spec-driven lessons layer.
+
+The LLM supplies judgment (which failure happened, how to phrase the lesson, what
+signal grounds it). This script owns everything mechanical: IDs, distinct-feature
+recurrence counting, candidate->confirmed promotion, pruning, demotion, and
+rendering the human/agent-readable playbook. Bookkeeping by hand is exactly what
+rots a lessons file, so it lives here, not in a prompt.
+
+Canonical state:  .specs/lessons.json   (machine-owned — do NOT hand-edit)
+Rendered view:    .specs/LESSONS.md      (regenerated on every write)
+
+Pure standard library. No dependencies. Run from the project root (the dir that
+contains .specs), or pass --root.
+
+Commands:
+  add        Record a grounded lesson from a verification signal.
+  list       Print lessons (default: confirmed) for loading at Specify/Design.
+  penalize   Mark a confirmed lesson as having failed when applied (-> quarantine).
+  prune      Drop stale uncorroborated candidates (also runs automatically on add/list).
+  status     Print counts (used by the self-check in validate.md).
+  init       Create empty store + rendered file.
+
+Exit codes: 0 ok, 2 usage/validation error (e.g. missing grounding).
+"""
+
+import argparse
+import datetime as _dt
+import json
+import os
+import re
+import sys
+
+STORE_REL = os.path.join(".specs", "lessons.json")
+RENDER_REL = os.path.join(".specs", "LESSONS.md")
+
+SIGNALS = {
+    "ac_gap": "Acceptance criterion not covered / failed",
+    "surviving_mutant": "Discrimination sensor mutant survived (weak test)",
+    "spec_precision_gap": "Spec did not define a precise outcome",
+    "spec_deviation": "Implementation diverged from spec/design (SPEC_DEVIATION)",
+    "gate_fail": "Build-level gate check failed",
+}
+
+DEFAULTS = {"promote_threshold": 2, "window_days": 45, "quarantine_threshold": 2}
+
+
+def _now():
+    return _dt.datetime.now(_dt.timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
+
+
+def _parse_date(s):
+    try:
+        return _dt.datetime.strptime(s, "%Y-%m-%dT%H:%M:%SZ").replace(tzinfo=_dt.timezone.utc)
+    except Exception:
+        return _dt.datetime.now(_dt.timezone.utc)
+
+
+def _store_path(root):
+    return os.path.join(root, STORE_REL)
+
+
+def _render_path(root):
+    return os.path.join(root, RENDER_REL)
+
+
+def _load(root):
+    path = _store_path(root)
+    if not os.path.exists(path):
+        return {
+            "schema": 1,
+            "promote_threshold": DEFAULTS["promote_threshold"],
+            "window_days": DEFAULTS["window_days"],
+            "quarantine_threshold": DEFAULTS["quarantine_threshold"],
+            "next_id": 1,
+            "lessons": [],
+        }
+    with open(path, "r", encoding="utf-8") as f:
+        data = json.load(f)
+    for k, v in DEFAULTS.items():
+        data.setdefault(k, v)
+    data.setdefault("schema", 1)
+    data.setdefault("next_id", 1)
+    data.setdefault("lessons", [])
+    return data
+
+
+def _save(root, data):
+    os.makedirs(os.path.join(root, ".specs"), exist_ok=True)
+    with open(_store_path(root), "w", encoding="utf-8") as f:
+        json.dump(data, f, indent=2, ensure_ascii=False)
+        f.write("\n")
+    _render(root, data)
+
+
+def _norm(text):
+    """Normalized dedup key: lowercase, strip punctuation, collapse whitespace.
+    Exact-after-normalization only — no semantic matching (stdlib-only limitation).
+    Phrase lessons tersely and canonically so recurrences actually merge."""
+    t = text.lower().strip()
+    t = re.sub(r"[^a-z0-9\s]", " ", t)
+    t = re.sub(r"\s+", " ", t).strip()
+    return t
+
+
+def _key(signal, text):
+    return signal + "::" + _norm(text)
+
+
+def _auto_prune(data):
+    """Drop candidates that never recurred within the window. Mutates data."""
+    threshold = data["promote_threshold"]
+    window = data["window_days"]
+    now = _dt.datetime.now(_dt.timezone.utc)
+    kept = []
+    dropped = []
+    for l in data["lessons"]:
+        if l["status"] == "candidate" and l["recurrence"] < threshold:
+            age_days = (now - _parse_date(l.get("last_seen", l.get("created", _now())))).days
+            if age_days > window:
+                dropped.append(l["id"])
+                continue
+        kept.append(l)
+    data["lessons"] = kept
+    return dropped
+
+
+def _find(data, signal, text):
+    k = _key(signal, text)
+    for l in data["lessons"]:
+        if l.get("key") == k:
+            return l
+    return None
+
+
+def _render(root, data):
+    lines = []
+    lines.append("# LESSONS — auto-maintained by scripts/lessons.py")
+    lines.append("")
+    lines.append("> Machine-owned. Do NOT hand-edit. Changes are overwritten on the next `lessons.py` write.")
+    lines.append("> Canonical state lives in `.specs/lessons.json`. Edit lessons only via the script.")
+    lines.append(f"> promote_threshold={data['promote_threshold']} distinct features · window_days={data['window_days']} · quarantine_threshold={data['quarantine_threshold']}")
+    lines.append("")
+
+    by_status = {"confirmed": [], "candidate": [], "quarantined": []}
+    for l in data["lessons"]:
+        by_status.get(l["status"], by_status["candidate"]).append(l)
+
+    def block(title, items, note):
+        out = [f"## {title}", ""]
+        if note:
+            out.append(note)
+            out.append("")
+        if not items:
+            out.append("_none_")
+            out.append("")
+            return out
+        for l in sorted(items, key=lambda x: x["id"]):
+            scope = f" · scope: `{l['scope']}`" if l.get("scope") else ""
+            out.append(f"### {l['id']} — {l['text']}")
+            out.append(
+                f"- signal: `{l['signal']}` · recurrence: {l['recurrence']} feature(s){scope} · harmful: {l.get('harmful', 0)}"
+            )
+            feats = ", ".join(l.get("features", [])) or "—"
+            out.append(f"- features: {feats}")
+            ev = l.get("evidence", [])
+            if ev:
+                out.append(f"- evidence: {ev[0]}" + (f" (+{len(ev) - 1} more)" if len(ev) > 1 else ""))
+            out.append(f"- last seen: {l.get('last_seen', '—')}")
+            out.append("")
+        return out
+
+    lines += block(
+        "Confirmed (load these at Specify/Design)",
+        by_status["confirmed"],
+        "Corroborated across multiple features. Safe to apply as guidance.",
+    )
+    lines += block(
+        "Candidates (under observation — do NOT load as guidance yet)",
+        by_status["candidate"],
+        "Seen once or not yet corroborated. Tracked, not trusted.",
+    )
+    lines += block(
+        "Quarantined (failed when applied — ignore)",
+        by_status["quarantined"],
+        "A confirmed lesson that recurred alongside failure. Kept for the maintainer to review.",
+    )
+
+    with open(_render_path(root), "w", encoding="utf-8") as f:
+        f.write("\n".join(lines).rstrip() + "\n")
+
+
+# ----------------------------- commands -----------------------------
+
+def cmd_init(root, args):
+    data = _load(root)
+    _save(root, data)
+    print(f"Initialized lessons store at {_store_path(root)} and {_render_path(root)}")
+    return 0
+
+
+def cmd_add(root, args):
+    signal = args.signal
+    source = (args.source or "").strip()
+    text = (args.text or "").strip()
+    feature = (args.feature or "").strip()
+
+    # Grounding is enforced here, deterministically — not left to the prompt.
+    if signal not in SIGNALS:
+        print(f"ERROR: --signal must be one of {sorted(SIGNALS)}", file=sys.stderr)
+        return 2
+    if not feature:
+        print("ERROR: --feature is required (the feature the signal came from).", file=sys.stderr)
+        return 2
+    if not source:
+        print("ERROR: --source is required (file:line / AC id / mutant id / SPEC_DEVIATION ref).", file=sys.stderr)
+        print("       A lesson with no grounding in validation.md is an opinion, not a lesson. Refused.", file=sys.stderr)
+        return 2
+    if len(text) < 12:
+        print("ERROR: --text too short. State the actionable lesson in one terse sentence.", file=sys.stderr)
+        return 2
+
+    data = _load(root)
+    _auto_prune(data)
+    existing = _find(data, signal, text)
+    now = _now()
+
+    if existing:
+        if feature not in existing["features"]:
+            existing["features"].append(feature)
+        existing["recurrence"] = len(existing["features"])
+        existing["last_seen"] = now
+        ev = source if not args.scope else f"{source} ({args.scope})"
+        if ev not in existing["evidence"]:
+            existing["evidence"].append(ev)
+        promoted = False
+        if existing["status"] == "candidate" and existing["recurrence"] >= data["promote_threshold"]:
+            existing["status"] = "confirmed"
+            promoted = True
+        _save(root, data)
+        msg = f"UPDATED {existing['id']} (recurrence={existing['recurrence']}, status={existing['status']})"
+        if promoted:
+            msg += " — PROMOTED to confirmed"
+        print(msg)
+    else:
+        lid = f"L-{data['next_id']:03d}"
+        data["next_id"] += 1
+        data["lessons"].append(
+            {
+                "id": lid,
+                "key": _key(signal, text),
+                "text": text,
+                "signal": signal,
+                "scope": (args.scope or "").strip(),
+                "status": "candidate",
+                "features": [feature],
+                "recurrence": 1,
+                "harmful": 0,
+                "evidence": [source if not args.scope else f"{source} ({args.scope})"],
+                "created": now,
+                "last_seen": now,
+            }
+        )
+        _save(root, data)
+        print(f"ADDED {lid} (status=candidate, recurrence=1)")
+    return 0
+
+
+def cmd_penalize(root, args):
+    data = _load(root)
+    target = None
+    for l in data["lessons"]:
+        if l["id"].lower() == args.id.lower():
+            target = l
+            break
+    if not target:
+        print(f"ERROR: no lesson with id {args.id}", file=sys.stderr)
+        return 2
+    target["harmful"] = target.get("harmful", 0) + 1
+    target["last_seen"] = _now()
+    if target["harmful"] >= data["quarantine_threshold"]:
+        target["status"] = "quarantined"
+    _save(root, data)
+    print(f"PENALIZED {target['id']} (harmful={target['harmful']}, status={target['status']})")
+    return 0
+
+
+def cmd_list(root, args):
+    data = _load(root)
+    if _auto_prune(data):
+        _save(root, data)
+    want = args.status
+    q = (args.query or "").lower().strip()
+    scope = (args.scope or "").lower().strip()
+    rows = []
+    for l in data["lessons"]:
+        if want != "all" and l["status"] != want:
+            continue
+        if q and q not in l["text"].lower():
+            continue
+        if scope and scope not in (l.get("scope", "").lower()):
+            continue
+        rows.append(l)
+    if not rows:
+        print(f"(no {want} lessons" + (f" matching '{q or scope}'" if (q or scope) else "") + ")")
+        return 0
+    for l in sorted(rows, key=lambda x: x["id"]):
+        sc = f" [scope:{l['scope']}]" if l.get("scope") else ""
+        print(f"{l['id']} ({l['status']}, x{l['recurrence']}){sc}: {l['text']}")
+    return 0
+
+
+def cmd_prune(root, args):
+    data = _load(root)
+    dropped = _auto_prune(data)
+    _save(root, data)
+    print(f"Pruned {len(dropped)} stale candidate(s): {', '.join(dropped) if dropped else '—'}")
+    return 0
+
+
+def cmd_status(root, args):
+    data = _load(root)
+    counts = {"confirmed": 0, "candidate": 0, "quarantined": 0}
+    for l in data["lessons"]:
+        counts[l["status"]] = counts.get(l["status"], 0) + 1
+    total = len(data["lessons"])
+    print(f"lessons: {total} total | confirmed={counts['confirmed']} candidate={counts['candidate']} quarantined={counts['quarantined']}")
+    return 0
+
+
+def main(argv=None):
+    p = argparse.ArgumentParser(prog="lessons.py", description="Deterministic lessons bookkeeping for spec-driven.")
+    p.add_argument("--root", default=".", help="Project root containing .specs/ (default: current dir)")
+    sub = p.add_subparsers(dest="cmd", required=True)
+
+    sp = sub.add_parser("init", help="Create empty store + rendered file")
+    sp.set_defaults(fn=cmd_init)
+
+    sp = sub.add_parser("add", help="Record a grounded lesson")
+    sp.add_argument("--feature", required=True)
+    sp.add_argument("--signal", required=True, choices=sorted(SIGNALS))
+    sp.add_argument("--source", required=True, help="file:line / AC id / mutant id / SPEC_DEVIATION ref")
+    sp.add_argument("--text", required=True, help="One terse, actionable sentence")
+    sp.add_argument("--scope", default="", help="Optional: path/layer/tag for retrieval filtering")
+    sp.set_defaults(fn=cmd_add)
+
+    sp = sub.add_parser("penalize", help="Mark a confirmed lesson as failed-when-applied")
+    sp.add_argument("--id", required=True)
+    sp.set_defaults(fn=cmd_penalize)
+
+    sp = sub.add_parser("list", help="Print lessons for loading")
+    sp.add_argument("--status", default="confirmed", choices=["confirmed", "candidate", "quarantined", "all"])
+    sp.add_argument("--query", default="", help="Substring filter on lesson text")
+    sp.add_argument("--scope", default="", help="Substring filter on scope")
+    sp.set_defaults(fn=cmd_list)
+
+    sp = sub.add_parser("prune", help="Drop stale uncorroborated candidates")
+    sp.set_defaults(fn=cmd_prune)
+
+    sp = sub.add_parser("status", help="Print counts")
+    sp.set_defaults(fn=cmd_status)
+
+    args = p.parse_args(argv)
+    root = os.path.abspath(args.root)
+    return args.fn(root, args)
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

package/skills/spec-loop/README.md

@@ -0,0 +1,36 @@
+# spec-loop
+
+Milestone-loop runner: drives every `.specs/` artifact to completion — ROADMAP → milestones → tasks → verification gates → atomic commits → STATE.md.
+
+| Field | Value |
+|-------|-------|
+| Version | 1.0.0 |
+| Trigger | "execute the specs", "run the plan", "loop the milestones" |
+| PT trigger | "executar as specs", "rodar o plano", "começar a executar", "siga o roadmap" |
+
+**Use when** a tlc-spec-driven project has pending `tasks.md` items and you want autonomous execution, milestone by milestone, with verification gates and atomic commits.
+
+**Do not use for** creating the plan itself — run [`spec-driven`](../spec-driven/README.md) first to produce the `.specs/` artifacts (ROADMAP.md, tasks.md, design.md, context.md), then hand execution to this skill.
+
+## The loop
+
+```
+ROADMAP.md → pending milestones (M0..Mn)
+  → feature tasks.md → atomic task
+      → execute → verify ("Verificar:" criteria) → atomic commit → STATE.md
+  → milestone gate (exit criteria) → next milestone
+→ final spec.md acceptance (Success Criteria) → project done
+```
+
+One task at a time, in tasks.md order — never skip a "Depends on" edge. Verification runs for real: red means fix or stop, never advance. STATE.md is updated after every task.
+
+## States
+
+- `⬜ planned` → `▶️ in progress` → `✅ done` | `🛑 blocked` (reason + evidence)
+- Milestone done only with green exit criteria; project done only with the spec.md final acceptance.
+
+## Resume
+
+Interrupted? Read STATE.md + recent commits → continue from the first non-done task. Never re-run tasks already done.
+
+See [SKILL.md](SKILL.md) for the full process (rules, gates, escalation, delegation).

package/skills/spec-loop/SKILL.md

@@ -0,0 +1,61 @@
+---
+name: spec-loop
+description: |
+  Drive the execution of every .specs/ artifact to completion — milestone by
+  milestone, task by task, with verification gates, atomic commits and STATE.md
+  progress tracking. Use when user says "execute the specs", "run the plan",
+  "loop the milestones", "executar as specs", "rodar o plano", "começar a
+  executar", "siga o roadmap", or when a tlc-spec-driven project has pending
+  tasks.md items and the user wants autonomous execution.
+license: CC-BY-4.0
+metadata:
+  author: runecraft
+  version: 1.0.0
+---
+
+# Spec Loop
+
+Executa todos os artefatos `.specs/` até a conclusão: ROADMAP → milestones → tasks → verificação → gates → commits atômicos → STATE.md.
+
+## Loop principal
+
+```
+ROADMAP.md → milestones pendentes (M0..Mn)
+  → tasks.md da feature → tarefa atômica
+      → executar → verificar (critério "Verificar:") → commit atômico → STATE.md
+  → gate do milestone (exit criteria) → próximo milestone
+→ acceptance final do spec.md (Success Criteria) → projeto done
+```
+
+## Regras (ordem de prioridade)
+
+1. **Ler antes de tocar**: ROADMAP.md (milestones), tasks.md (tarefas e dependências), design.md (tabelas de mapeamento são fonte da verdade), context.md (decisões AD-* são fechadas).
+2. **Uma tarefa por vez**, na ordem do tasks.md; nunca pule uma dependência (campo "Depends on").
+3. **Verificar antes de avançar**: toda tarefa tem critérios `**Verificar:**` — rode-os de fato; verificação vermelha = corrigir ou parar, nunca avançar.
+4. **Commits atômicos** por tarefa concluída; mensagem com o REQ-ID/ID da tarefa quando existir.
+5. **STATE.md atualizado após cada tarefa** (done/blocked + riscos novos observados).
+6. **Safety valve**: se uma tarefa revelar >5 passos inesperados ou novas dependências → PARE e estenda tasks.md antes de continuar.
+7. **Escalação**: blocker real → pare e reporte ao usuário com evidência; nenhuma decisão AD-* muda silenciosamente.
+8. **Gates de milestone**: exit criteria do ROADMAP + grep guards (design.md §8) verdes antes de marcar o milestone como done.
+9. **Escopo cirúrgico**: só arquivos da tarefa; nunca edite clones de referência, repos externos ou histórico git.
+10. **Delegação opcional**: fatias mecânicas extensas → fighter/ranger; review de milestones → cleric. O loop permanece no agente principal.
+
+## Estados
+
+- `⬜ planned` → `▶️ in progress` → `✅ done` | `🛑 blocked` (motivo + evidência)
+- Milestone done somente com exit criteria verdes.
+- Projeto done somente com a acceptance final do spec.md.
+
+## Retomada
+
+Se interrompido: leia STATE.md + últimos commits → continue da primeira tarefa não-done. Nunca re-execute tarefas já done.
+
+## Exemplo (Squad)
+
+```
+ROADMAP: M0 → M1 → {M2, M3} → M4 · M5 ∥ M4
+1. M0: T-M0-01 (repo init) → verificar git status → commit → STATE.md
+2. M0: T-M0-02..05 → gate M0 (exit criteria) → M0 ✅
+3. M1: T-M1-01..12 (sweep) → full suite + grep guards → M1 ✅
+...até a acceptance final de spec.md
+```

package/skills/test-driven-development/README.md

@@ -0,0 +1,13 @@
+# test-driven-development
+
+Drive development with tests. Fail first, make them pass, then refactor.
+
+| Field | Value |
+|-------|-------|
+| Version | 1.0.0 |
+| Trigger | `/test`, "TDD", "prove it", "80/15/5 pyramid", "Beyonce Rule" |
+| PT trigger | `/teste`, "testes primeiro", "provar com teste" |
+
+**Do not use for** production incident triage (use `/debug`) or cosmetic-only changes with no behavioral surface.
+
+See [SKILL.md](SKILL.md) for the full process, and [references/testing-patterns.md](../../references/testing-patterns.md) for common testing patterns and the 80/15/5 pyramid.