@antoneeo/mkt-agentic-sdlc-skill 0.17.0 → 0.19.0

package/CHANGELOG.md

@@ -1,5 +1,16 @@
 # Changelog
 
+## [0.19.0] - 2026-10-17
+
+### Changed
+- F-073 (shared validator and doctrine): one written form for a dated entry, `**YYYY-MM-DD — label.**`, is taught for spike outcomes and project notes that record an event, and shared readers let a chronology list those events the same way the validator reads them. Two advisories reach marketing, and neither fails a build, not even `--strict`: a HANDOFF `next:` longer than 240 characters on a `level: L3` file updated on or after 2026-10-18 (`next:` now holds only the next step), and, in `check`, an open L3 unit whose id another branch or tag uses for a different analysis. That id check identifies a unit by its ANALYSIS file; a marketing request record names none, so an engagement without an ANALYSIS is not checked yet. The doctrine now says to choose a new id after fetching, and that a session sharing a checkout with another session works in its own git worktree. Advisories print as `[advisory]` lines and never count toward the exit code.
+
+## [0.18.0] - 2026-10-17
+
+### Changed
+- F1: closing the last open workstream now empties the generated registry `audit/handoff.md` instead of leaving its stale row behind: with zero `HANDOFF_*.md` sources `index` rewrites it empty (keeping `project_notes.md`), and `validate` reports a generated registry that still has rows but no sources as an error.
+- F-069: `graph`, `check`, `stale` and the session-start count are faster on a mature knowledge base, with byte-identical output. Citations of superseded claim ids are found with one pass per living document instead of one scan per (document, id) pair, and one check run reads and resolves each cited extraction once instead of once per claim row. On a synthetic ledger of 2183 rows and 1000 living documents, `graph` drops from 14 s to 4 s. No new flag.
+
 ## [0.17.0] - 2026-10-13
 
 ### Changed

package/gemini-extension.json

@@ -1,6 +1,6 @@
 {
   "name": "mkt-agentic-sdlc",
-  "version": "0.17.0",
+  "version": "0.19.0",
   "description": "Evidence-First marketing planning protocol with engagement triage, SOSTAC workflow, evidence ledger and optional devPNT integration.",
   "author": "Antonio Pinto (https://github.com/Antoneeo)"
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@antoneeo/mkt-agentic-sdlc-skill",
-  "version": "0.17.0",
+  "version": "0.19.0",
   "description": "Evidence-First marketing planning protocol for Claude Code, Gemini CLI, Google Antigravity and Codex: engagement triage, SOSTAC workflow, evidence ledger, mechanical validator and optional devPNT integration.",
   "keywords": [
     "claude-code",

package/scripts/init.js

@@ -194,16 +194,16 @@ in the skill's \`routing.md\`: it decides which lens's method and validation rul
 that unit. L1 never reaches it. Never refer to a document whose meaning differs by lens
 ("threat model", "vision", \`principles.md\`, \`handoff.md\`) by its bare name.
 
-Select the owning lens by the unit's purpose, then apply only its risk scale.
-The project's always-on pointer stays intact: consult the selected skill rather than
-merging multiple mandatory ladders. All lenses already carry shared project memory
-(\`memory.md\`); another installation is not needed for cross-domain recall.
+Select the owning lens by the unit's purpose, then apply only its risk scale.
+The project's always-on pointer stays intact: consult the selected skill rather than
+merging multiple mandatory ladders. All lenses already carry shared project memory
+(\`memory.md\`); another installation is not needed for cross-domain recall.
 This file is NOT auto-loaded by any client: it is a note for you, deliberately additive.
-Delete this note once the routing pointer is integrated.
+Delete this note once the routing pointer is integrated.
 `, 'multi-lens routing note');
   if (wrote && protocolPreexisting) {
     console.log('   ⚠️  A protocol pointer already existed and was NOT overwritten.');
-    console.log('       Integrate the routing pointer from AGENTIC_MULTI_LENS.md; keep one risk scale per unit.');
+    console.log('       Integrate the routing pointer from AGENTIC_MULTI_LENS.md; keep one risk scale per unit.');
   }
 }
 

package/skills/mkt-agentic-sdlc/ENFORCEMENT.md

@@ -14,17 +14,17 @@ python "<skill_dir>/scripts/mkt_check.py" check
 
 ## 2. Check in CI (recommended for teams)
 
-Copy all three validator files into the repository: `scripts/mkt_check.py`, `scripts/sdlc_core.py`, and `scripts/knowledge.py`, keeping them side by side. Then add to the pipeline:
+Copy all three validator files into the repository: `scripts/mkt_check.py`, `scripts/sdlc_core.py`, and `scripts/knowledge.py`, keeping them side by side. Then add to the pipeline:
 
 ```
 python tools/mkt_check.py validate --strict
 ```
 
-The validator ships as **three files**: the domain entry point, `sdlc_core.py` and `knowledge.py`. Keep all three together. The core alone still runs but omits shared-memory/KB checks and domain-specific overlays; it is not an equivalent CI gate. `check` includes the knowledge surface when present.
+The validator ships as **three files**: the domain entry point, `sdlc_core.py` and `knowledge.py`. Keep all three together. The core alone still runs but omits shared-memory/KB checks and domain-specific overlays; it is not an equivalent CI gate. `check` includes the knowledge surface when present.
 
 Effect: an unregenerated index, invalid frontmatter, a missing security section or incoherent states **block the pipeline** instead of relying on the agent's memory. `--strict` also fails on warnings and on a missing `ai_docs/`, so a wrong working directory cannot produce a green pipeline. This works because documents travel in the same PR as the code (Phase 5 rule).
 
-Note: the copy in the repo is the authoritative one for CI; update it when you update the skill — all three files, together.
+Note: the copy in the repo is the authoritative one for CI; update it when you update the skill — all three files, together.
 
 **Projects whose docs root is not `ai_docs/`.** Pass `--docs-dir <name>` (e.g. `--docs-dir mkt_docs`) on any subcommand, or set `AGENTIC_SDLC_DOCS_DIR`. Without either, the validator walks up from the working directory and takes the nearest root it recognizes. If it finds two side by side — the shape of a half-finished migration — it refuses and names both rather than validating half a project and printing a verdict. `ai_docs/` remains the default and the recommended root: the parameter exists so a legacy tree can be read and migrated, not so a second one can be kept.
 
@@ -155,7 +155,7 @@ Gemini CLI — wire the same command into its startup-hook mechanism if present;
 **Usage notes:**
 - The hook assumes the working directory is the project root (standard Claude Code hook behavior); it also accepts `--root <path>`.
 - **Hybrid/devPNT projects**: add `--hybrid` — the hook then appends a one-line pointer to run `devpnt_mcp_get_bootstrap` for the Master Plan / Knowledge Layer and does not replicate them; the filesystem orientation (router + handoff + README) still emits.
-- Like the CI gate (§2), if you copied the validator into the repo, the hook references that copy — keep all three files current when you update the skill.
+- Like the CI gate (§2), if you copied the validator into the repo, the hook references that copy — keep all three files current when you update the skill.
 
 ### Per-turn reminder: `remind` (UserPromptSubmit -- wired by default)
 
@@ -215,7 +215,7 @@ It aggregates the test files (`test_plan.py` + `test_session_start.py` + `test_s
 
 **Optional CI** (same shape as §2, not mandatory): add a `run:` step invoking the `unittest discover` command above.
 
-**T10 note:** if you copied the validator (all three files) and the `test_*.py` battery into the repo for CI, that copy is authoritative — keep it current when you update the skill.
+**T10 note:** if you copied the validator (all three files) and the `test_*.py` battery into the repo for CI, that copy is authoritative — keep it current when you update the skill.
 
 ## `benefit` is a report, never a CI gate
 

package/skills/mkt-agentic-sdlc/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: mkt-agentic-sdlc
-version: 0.17.0
+version: 0.19.0
 description: Evidence-First marketing planning protocol with engagement triage, SOSTAC workflow, evidence ledger, adversarial CMO review, a complete Standalone mode and optional symbiosis with devPNT. Use for marketing plans, go-to-market strategy, campaign planning and market research.
 author: Antonio Pinto (https://github.com/Antoneeo)
 copyright: (c) 2026 Antonio Pinto
@@ -79,7 +79,7 @@ One event, one destination: when the trigger fires and the document does not exi
 |---|---|---|
 | `audit/requests/REQUEST_[engagement].md` | Every E3, the moment the level is declared — before Wave 1 and the Vision Gate: R1 quotes the client's opening words verbatim; every later statement of theirs that settles something (answer, approval, budget, ruling) is appended before acting on it. Append-only, never deleted; artifacts and owner-given `FACT` rows cite its entries (`templates.md`). | 1 → 9 |
 | `audit/handoff.md` (workstream registry) | **Never by hand — generated by `mkt_check.py index` from the `HANDOFF_*.md` sources**, and `validate` errors when the two disagree. Regenerate at every closure and at session end; the `Date:` header is derived, so no writer touches it. Inventory for lookup, never a work board. | 9 / session end |
-| `audit/HANDOFF_[engagement].md` | **One per OPEN engagement, with or without volatile state** — it is the authored home of that engagement's registry row (frontmatter `workstream`/`level`/`branch`/`status`/`since`/`next`/`details`/`updated`), so no file means no row. DELETED at closure — deleting it *is* removing the row. | 9 / session end |
+| `audit/HANDOFF_[engagement].md` | **One per OPEN engagement, with or without volatile state** — it is the authored home of that engagement's registry row (frontmatter `workstream`/`level`/`branch`/`status`/`since`/`next`/`details`/`updated`), so no file means no row. Its `next:` is the next concrete step in one sentence; what happened, and the state of the work, go to the Diary as a dated entry. DELETED at closure — deleting it *is* removing the row. | 9 / session end |
 | `audit/project_notes.md` | A note true for the whole engagement portfolio rather than one engagement. Appended verbatim to the generated registry, so regenerating cannot destroy it. | 9 / session end |
 | `audit/handoff.md` — converting an existing project | **Lazily, at the first write — and then ALL AT ONCE.** Converting one row at a time is the state that loses the others, so `index` refuses to write while anything in the file is unaccounted for and names it. | 9 / session end |
 | `audit/HANDOFF_[engagement].md` | Session ends with that engagement unfinished AND there is volatile resume state. Ephemeral, deleted at closure. | 8 / 9 / session end |
@@ -167,7 +167,7 @@ Deliverable language: ask for (or infer) the target market's language in Discove
 - `mkt_check.py budget && mkt_check.py funnel && mkt_check.py trace` must pass. A tactic that serves no objective is deleted or the objective set is revisited — never silently kept.
 
 ### 8. Action
-- **Isolate the work (Branch/worktree hygiene).** Execution rewrites plan documents other people are reading: do it on a branch or a worktree, never directly on the shared plan.
+- **Isolate the work (Branch/worktree hygiene).** Execution rewrites plan documents other people are reading: do it on a branch or a worktree, never directly on the shared plan. A session that may run while another session uses the same checkout works in its **own git worktree**, and never switches branch, stashes, resets or runs `index` in a checkout another session may be using. Parallel work also shares ids: choose a new unit's id **after fetching**, as the first id free on every branch and tag the checkout can see.
 - **Consult (before acting)**: **consult the guide router** for a guide covering the task and read it first (the consult trigger, `guides.md` §0). A targeted description match, not a blanket read.
 - **Opt-in subagent execution**: for an approved plan, the work MAY be executed via subagents per `dispatch.md`; default stays same-session. `dispatch.md` also carries the family-wide **delegation boundary** (what may be delegated at all, and what never may) — that section is not gated by the opt-in trigger and applies at any level, dispatch or no dispatch.
 - Draft `ACTION_90D.md`: sequenced 90-day plan (what starts when, owner, dependency), first 2 weeks day-level, rest weekly.

package/skills/mkt-agentic-sdlc/scripts/knowledge.py

@@ -125,6 +125,21 @@ def kb_unquote(value):
     return v
 
 
+def frontmatter_date(meta):
+    """A note's or a sidecar's `date:` as `YYYY-MM-DD`, or None (F-073).
+    Quotes stripped, a datetime suffix tolerated, an impossible date refused --
+    the one parser behind orient's recency probe and any chronology reader."""
+    m = re.match(r"(\d{4}-\d{2}-\d{2})", kb_unquote((meta or {}).get("date")))
+    if not m:
+        return None
+    try:
+        import datetime as _dt
+        _dt.date.fromisoformat(m.group(1))
+    except ValueError:
+        return None
+    return m.group(1)
+
+
 def kb_parse_scope(text):
     """'-' | 'from X' | 'until X' | 'from X until Y' | 'if <cond>' ->
     ('always',) | ('window', from, until) | ('if', cond). Raises on junk."""
@@ -336,6 +351,17 @@ def kb_check_claims(root):
         if rel not in fm_cache:
             fm_cache[rel] = _note_frontmatter(root, rel)
         return fm_cache[rel]
+    # F-069: the same per-run memo for the source paths themselves -- each
+    # distinct path is resolved and stat'ed once, and each cited extraction
+    # read once (loc_cache, owned here, dropped when this call returns).
+    src_cache = {}
+    loc_cache = {}
+
+    def _resolved(path_s):
+        if path_s not in src_cache:
+            t = sdlc_core.confine_under(root, path_s)
+            src_cache[path_s] = (t, t is not None and t.is_file())
+        return src_cache[path_s]
     per_file_rows = []
     for p in sorted(topics.glob("*.md")):
         rel = "topics/" + p.name
@@ -357,16 +383,16 @@ def kb_check_claims(root):
                     errors.append("%s: source %r has no locator" % (where, src))
                     continue
                 path_s, loc = src.rsplit("#", 1)
-                target = sdlc_core.confine_under(root, path_s)
+                target, is_file = _resolved(path_s)
                 if target is None:
                     errors.append("%s: source %r escapes the docs root" % (where, src))
                     continue
-                if not target.is_file():
+                if not is_file:
                     errors.append("%s: source %r does not resolve — a claim whose "
                                   "origin cannot be reopened is model knowledge"
                                   % (where, src))
                     continue
-                kb_check_locator(target, loc, where, errors)
+                kb_check_locator(target, loc, where, errors, loc_cache)
             # --- provenance ---
             prov = row["prov"]
             # Resolved ONCE, for every provenance: the non-GIVEN classes read it
@@ -556,8 +582,14 @@ def kb_check_claims(root):
     return errors, warnings, notes
 
 
-def kb_check_locator(target, loc, where, errors):
-    """A locator must address an existing span of the stored bytes."""
+def kb_check_locator(target, loc, where, errors, cache=None):
+    """A locator must address an existing span of the stored bytes.
+
+    `cache` is an optional dict the CALLER owns for one run (F-069): keyed by
+    the path actually read, it holds only what the checks compare against --
+    page lengths, a line count, or False for a missing extraction -- never the
+    text. Findings are still appended per call, so per row. Without it, every
+    call reads the file, as before."""
     m = LOC_PAGE_RE.match(loc)
     if m:
         page, a, b = int(m.group(1)), int(m.group(2)), int(m.group(3))
@@ -566,17 +598,24 @@ def kb_check_locator(target, loc, where, errors):
             return
         # offsets address the stored extraction (<stem>.txt beside the original)
         ext = target if target.suffix == ".txt" else target.with_suffix(".txt")
-        if not ext.is_file():
+        key = ("p", ext)
+        if cache is None or key not in cache:
+            lengths = ([len(pg) for pg in sdlc_core.read_text(ext).split("\f")]
+                       if ext.is_file() else False)
+            if cache is not None:
+                cache[key] = lengths
+        else:
+            lengths = cache[key]
+        if lengths is False:
             errors.append("%s: no stored extraction %s for locator %r — offsets "
                           "must address kept bytes" % (where, ext.name, loc))
             return
-        pages = sdlc_core.read_text(ext).split("\f")
-        if page < 1 or page > len(pages):
+        if page < 1 or page > len(lengths):
             errors.append("%s: locator %r addresses page %d of %d" %
-                          (where, loc, page, len(pages)))
-        elif b > len(pages[page - 1]):
+                          (where, loc, page, len(lengths)))
+        elif b > lengths[page - 1]:
             errors.append("%s: locator %r spans past the end of page %d "
-                          "(%d chars)" % (where, loc, page, len(pages[page - 1])))
+                          "(%d chars)" % (where, loc, page, lengths[page - 1]))
         return
     m = LOC_LINE_RE.match(loc)
     if m:
@@ -584,7 +623,13 @@ def kb_check_locator(target, loc, where, errors):
         if a > b or a < 1:
             errors.append("%s: locator %r has an invalid line range" % (where, loc))
             return
-        n = sdlc_core.read_text(target).count("\n") + 1
+        key = ("L", target)
+        if cache is None or key not in cache:
+            n = sdlc_core.read_text(target).count("\n") + 1
+            if cache is not None:
+                cache[key] = n
+        else:
+            n = cache[key]
         if b > n:
             errors.append("%s: locator %r spans past line %d" % (where, loc, n))
         return
@@ -1085,12 +1130,18 @@ KB_GENERATED_RE = re.compile(r"GENERATED by \S+ index - do not edit by hand")
 KB_HEX12_RE = re.compile(r"^[0-9a-f]{12}$")
 
 
-def _kb_hex_bounded(text, cid):
-    """True when cid appears NOT embedded in a longer hex run: a git hash
-    sharing a substring must never count as a citation (either side, either
-    case). cid is pre-validated 12-hex, so it is regex-safe by construction."""
-    return re.search(r"(?<![0-9a-fA-F])%s(?![0-9a-fA-F])" % cid,
-                     text) is not None
+# A citation of a claim id is a run of exactly its 12 lowercase hex characters
+# NOT embedded in a longer hex run: a git hash sharing a substring must never
+# count as a citation (either side, either case). Two such bounded runs cannot
+# overlap, so findall returns every one of them.
+KB_HEX_TOKEN_RE = re.compile(r"(?<![0-9a-fA-F])[0-9a-f]{12}(?![0-9a-fA-F])")
+
+
+def _kb_hex_tokens(text):
+    """The ids a text cites, extracted in one pass (F-069). Callers test
+    membership instead of scanning the text once per id: that per-(document,
+    id) scan made the time cycle grow with superseded ids x living documents."""
+    return frozenset(KB_HEX_TOKEN_RE.findall(text))
 
 
 def _kb_df_entries(value):
@@ -1172,19 +1223,23 @@ def kb_time_cycle(docs):
         if (meta.get("status") or "").strip() == "SUPERSEDED":
             continue
         living.append((rel, text))
-    for rel, text in living:
-        for old in sorted(superseded):
-            if _kb_hex_bounded(text, old):
-                succs = superseded[old]
-                missing = tuple(x for x in succs
-                                if not _kb_hex_bounded(text, x))
-                if missing:
-                    cited.append((rel, old, missing, succs))
+    # One token pass per living document, and none at all on a KB with no
+    # supersession and no validity window (the orient line runs this at every
+    # session start).
+    tokens = ({rel: _kb_hex_tokens(text) for rel, text in living}
+              if superseded or windows else {})
+    for rel, _text in living:
+        cites = tokens[rel] if tokens else frozenset()
+        for old in cites.intersection(superseded):
+            succs = superseded[old]
+            missing = tuple(x for x in succs if x not in cites)
+            if missing:
+                cited.append((rel, old, missing, succs))
     today = _dt.date.today().isoformat()
     for topic_rel, rid, until in sorted(windows):
         if until <= today:
-            by = tuple(rel for rel, text in living
-                       if rel != topic_rel and _kb_hex_bounded(text, rid))
+            by = tuple(rel for rel, _text in living
+                       if rel != topic_rel and rid in tokens[rel])
             expired.append((topic_rel, rid, until, by))
     rev = {}
     node_meta = {}
@@ -1905,14 +1960,13 @@ def kb_cmd_orient(argv):
                     # it -- the file was already fully read, so the cap bought
                     # only failure. load_frontmatter is the authoritative
                     # reader (fence-bounded, so a column-0 date: in the body
-                    # still cannot misdate the note); kb_unquote covers quoted
-                    # dates; the prefix match tolerates a datetime suffix.
+                    # still cannot misdate the note); frontmatter_date covers
+                    # quoted dates and tolerates a datetime suffix.
                     meta = sdlc_core.load_frontmatter(
                         sdlc_core.read_text(p).splitlines()) or {}
-                    m = re.match(r"(\d{4}-\d{2}-\d{2})",
-                                 kb_unquote(meta.get("date")))
-                    if m:
-                        stamp = _dt.date.fromisoformat(m.group(1))
+                    day = frontmatter_date(meta)
+                    if day:
+                        stamp = _dt.date.fromisoformat(day)
                 except Exception:
                     pass
                 if stamp is None:

package/skills/mkt-agentic-sdlc/scripts/mkt_check.py

@@ -735,6 +735,15 @@ def main(argv=None):
             code = max(code, sdlc_core.cmd_validate(root, strict=args.strict))
         code = max(code, knowledge.kb_validate_surface(root / sdlc_core.docs_dir(),
                                                        full=args.command == "check"))
+        # F-073 advisories: Report has no advisory channel and --strict fails on
+        # any warning, so they print here, outside Report, never in `code`. On an
+        # ai_docs root cmd_validate above already printed A1/A2 -- once is the
+        # contract. A3 has no other path: this overlay never calls cmd_check.
+        notes = [] if sdlc_core.docs_dir() == "ai_docs" else sdlc_core.chronology_advisories(root)
+        if args.command == "check":
+            notes += sdlc_core.id_advisories(root)
+        for a in notes:
+            print(f"[advisory] {a}")
     if code == 0:
         print(f"[OK] {args.command} clean "
               f"({len(rep.warnings)} warning(s))" if rep.warnings else f"[OK] {args.command} clean")