threadkeeper 0.17.3__tar.gz → 0.17.5__tar.gz

{threadkeeper-0.17.3 → threadkeeper-0.17.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: threadkeeper
-Version: 0.17.3
+Version: 0.17.5
 Summary: Multi-agent shared brain across Claude Code/Desktop, Codex, Antigravity CLI, Copilot, and VS Code. Cross-session memory, self-improving skill loops, inter-agent signaling — one local MCP server.
 Author: thread-keeper contributors
 License: MIT
@@ -310,6 +310,12 @@ uses a SQLite `BEGIN IMMEDIATE` reservation: `spawn()` re-checks the budget and
 inserts the child task row with its RSS estimate before `Popen`, so two
 concurrent spawns cannot both squeeze through the cap.
 
+When `cwd` is inside a Git checkout, `spawn()` also requires the source
+checkout's tracked files to be clean, then starts the child from a unique
+branch/worktree under `THREADKEEPER_TASK_LOG_DIR/worktrees/`. Parallel children
+therefore never share a mutable checkout or Git index. Non-Git directories keep
+their existing behavior; a dirty Git checkout is refused before a child starts.
+
 The spawn wrapper also records each completed child's `duration_s`,
 `tokens_in`, `tokens_out`, `tokens_total`, and `cost_usd` when the underlying
 CLI emits a recognizable usage trailer. Optional daily ceilings
@@ -605,7 +611,9 @@ can correct one unique substring without reserializing a lesson. Shadow-origin
 though an existing same-slug long lesson may be corrected without increasing
 its body size; near-duplicate slugs are blocked, and semantic body matches are
 routed to the incumbent lesson or surfaced for curation instead of minting a
-sibling lesson.
+sibling lesson. A clear new directive or debunk also flags older permissive
+lessons on the same concrete practice for patch, cross-link, or supersession
+review.
 
 #### 3. Extract daemon
 
@@ -710,6 +718,12 @@ non-forced direct `curator_review()` calls return `not_due` inside the
 configured interval and record that status without spawning. A manual
 `curator_review(force=True)` bypasses the interval but still respects the lock.
 
+For automation-created skills, the audit keeps foreground consultation separate
+from maintenance: a background-review skill with `fg_uses=0` after 14 days is
+still a false-positive prune candidate even if automatic review or sync loops
+have increased its patch counter. Patches are maintenance activity, not proof
+that a foreground user or agent consulted the skill.
+
 Before spawning, the scheduler hashes lessons, concepts, skill bodies, support
 trees, validators, and mirror state. Repeated manual calls over identical bytes
 return `unchanged_inventory`; the scheduled three-day pass still runs because
@@ -1549,8 +1563,9 @@ Spawn task spool files live in `THREADKEEPER_TASK_LOG_DIR` (default
 the hardened `~/.threadkeeper` perimeter by default; explicit overrides are
 refused when the configured directory is a symlink or is not owned by the
 current user. `spawn()` creates captured headless `.log`, stdin prompt spool,
-and visible `.command` files with no-follow owner-only opens. `consolidate()`
-garbage-collects task spool files once their task row is no longer retained.
+and visible `.command` files with no-follow owner-only opens. Git-backed spawns
+also create their isolated worktrees there. `consolidate()` garbage-collects
+task spool files once their task row is no longer retained.
 
 ---
 

{threadkeeper-0.17.3 → threadkeeper-0.17.5}/README.md

@@ -266,6 +266,12 @@ uses a SQLite `BEGIN IMMEDIATE` reservation: `spawn()` re-checks the budget and
 inserts the child task row with its RSS estimate before `Popen`, so two
 concurrent spawns cannot both squeeze through the cap.
 
+When `cwd` is inside a Git checkout, `spawn()` also requires the source
+checkout's tracked files to be clean, then starts the child from a unique
+branch/worktree under `THREADKEEPER_TASK_LOG_DIR/worktrees/`. Parallel children
+therefore never share a mutable checkout or Git index. Non-Git directories keep
+their existing behavior; a dirty Git checkout is refused before a child starts.
+
 The spawn wrapper also records each completed child's `duration_s`,
 `tokens_in`, `tokens_out`, `tokens_total`, and `cost_usd` when the underlying
 CLI emits a recognizable usage trailer. Optional daily ceilings
@@ -561,7 +567,9 @@ can correct one unique substring without reserializing a lesson. Shadow-origin
 though an existing same-slug long lesson may be corrected without increasing
 its body size; near-duplicate slugs are blocked, and semantic body matches are
 routed to the incumbent lesson or surfaced for curation instead of minting a
-sibling lesson.
+sibling lesson. A clear new directive or debunk also flags older permissive
+lessons on the same concrete practice for patch, cross-link, or supersession
+review.
 
 #### 3. Extract daemon
 
@@ -666,6 +674,12 @@ non-forced direct `curator_review()` calls return `not_due` inside the
 configured interval and record that status without spawning. A manual
 `curator_review(force=True)` bypasses the interval but still respects the lock.
 
+For automation-created skills, the audit keeps foreground consultation separate
+from maintenance: a background-review skill with `fg_uses=0` after 14 days is
+still a false-positive prune candidate even if automatic review or sync loops
+have increased its patch counter. Patches are maintenance activity, not proof
+that a foreground user or agent consulted the skill.
+
 Before spawning, the scheduler hashes lessons, concepts, skill bodies, support
 trees, validators, and mirror state. Repeated manual calls over identical bytes
 return `unchanged_inventory`; the scheduled three-day pass still runs because
@@ -1505,8 +1519,9 @@ Spawn task spool files live in `THREADKEEPER_TASK_LOG_DIR` (default
 the hardened `~/.threadkeeper` perimeter by default; explicit overrides are
 refused when the configured directory is a symlink or is not owned by the
 current user. `spawn()` creates captured headless `.log`, stdin prompt spool,
-and visible `.command` files with no-follow owner-only opens. `consolidate()`
-garbage-collects task spool files once their task row is no longer retained.
+and visible `.command` files with no-follow owner-only opens. Git-backed spawns
+also create their isolated worktrees there. `consolidate()` garbage-collects
+task spool files once their task row is no longer retained.
 
 ---
 

{threadkeeper-0.17.3 → threadkeeper-0.17.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "threadkeeper"
-version = "0.17.3"
+version = "0.17.5"
 description = "Multi-agent shared brain across Claude Code/Desktop, Codex, Antigravity CLI, Copilot, and VS Code. Cross-session memory, self-improving skill loops, inter-agent signaling — one local MCP server."
 requires-python = ">=3.11"
 authors = [{ name = "thread-keeper contributors" }]

{threadkeeper-0.17.3 → threadkeeper-0.17.5}/tests/test_curator.py

@@ -152,15 +152,15 @@ def test_collect_inventory_counts_lessons_and_skills(tmp_path, monkeypatch):
     conn.execute(
         "INSERT INTO skill_usage "
         "(name, created_at, created_by_origin, last_used_at, "
-        " use_count, pinned, state) "
-        "VALUES (?, ?, 'foreground', ?, 5, 1, 'active')",
+        " use_count, foreground_use_count, view_count, pinned, state) "
+        "VALUES (?, ?, 'foreground', ?, 5, 4, 3, 1, 'active')",
         ("pinned-skill", now - 86400, now - 3600),
     )
     conn.execute(
         "INSERT INTO skill_usage "
         "(name, created_at, created_by_origin, last_used_at, "
-        " use_count, state) "
-        "VALUES (?, ?, 'background_review', ?, 2, 'active')",
+        " use_count, foreground_use_count, view_count, state) "
+        "VALUES (?, ?, 'background_review', ?, 2, 1, 6, 'active')",
         ("auto-created-skill", now - 172800, now - 7200),
     )
     conn.commit()
@@ -177,6 +177,8 @@ def test_collect_inventory_counts_lessons_and_skills(tmp_path, monkeypatch):
     # background_review skill (not pinned) is NOT protected
     assert "SKILL auto-created-skill [PROTECTED]" not in dump
     assert "SKILL auto-created-skill" in dump
+    assert "fg_uses=4 uses=5 views=3 maintenance_patches=0" in dump
+    assert "fg_uses=1 uses=2 views=6 maintenance_patches=0" in dump
     assert "STALE LESSONS (dry-run decay ranking)" in dump
 
 
@@ -843,6 +845,48 @@ def test_skill_validator_is_exhaustive_and_semantic(tmp_path, monkeypatch):
     assert "3. SKILL second-skill" in checklist
 
 
+def test_curator_prune_rubric_keeps_patched_unconsulted_skill_eligible(
+    tmp_path, monkeypatch,
+):
+    pkg = _bootstrap(tmp_path, monkeypatch, min_lessons="2")
+    pkg["lessons"].append_lesson(title="one", body="b1", source="shadow")
+    pkg["lessons"].append_lesson(title="two", body="b2", source="shadow")
+    _write_audit_skill(
+        pkg["skills_dir"], "patched-background-skill", "# Rule\nDo the test.",
+    )
+    now = int(time.time())
+    conn = pkg["db"].get_db()
+    conn.execute(
+        "INSERT INTO skill_usage "
+        "(name, created_at, created_by_origin, last_patched_at, patch_count, "
+        "foreground_use_count, state) VALUES (?, ?, ?, ?, ?, ?, ?)",
+        (
+            "patched-background-skill", now - 30 * 86400,
+            "background_review", now, 4, 0, "active",
+        ),
+    )
+    conn.commit()
+
+    import threadkeeper.tools.spawn as spawn_mod
+    captured: list[dict] = []
+
+    def fake_spawn(**kwargs):
+        captured.append(kwargs)
+        return "spawn task_id=patched-background-skill pid=0"
+
+    monkeypatch.setattr(spawn_mod, "spawn", fake_spawn)
+    pkg["curator"].run_curator_pass(force=True)
+
+    prompt = captured[0]["prompt"]
+    assert "origin=background_review AND fg_uses=0" in prompt
+    assert "they are not foreground consultation" in prompt
+    assert "SKILL patched-background-skill" in prompt
+    assert "fg_uses=0" in prompt
+    assert "maintenance_patches=4" in prompt
+    assert "created=30d_ago" in prompt
+    assert "patches=0" not in prompt
+
+
 def test_skill_validate_tool_returns_post_change_contract(tmp_path, monkeypatch):
     pkg = _bootstrap(tmp_path, monkeypatch)
     primary = pkg["skills_dir"]

{threadkeeper-0.17.3 → threadkeeper-0.17.5}/tests/test_lessons.py

@@ -356,6 +356,74 @@ def test_shadow_lesson_append_semantic_duplicate_patches_incumbent(
     assert "serialize AVD boot lock acquisition" in body
 
 
+def test_new_directive_flags_older_permissive_lesson_for_reconciliation(
+    tmp_path, monkeypatch,
+):
+    pkg = _bootstrap(tmp_path, monkeypatch, write_origin="shadow_review")
+    la = _tool(pkg, "lesson_append")
+
+    first = la(
+        title="module globals for test configuration",
+        body=(
+            "You can use module globals to pass test configuration between "
+            "runner steps when setup is simple."
+        ),
+        source="shadow",
+    )
+    assert first.startswith("ok")
+
+    out = la(
+        title="inject test configuration explicitly",
+        body=(
+            "Never use module globals to pass test configuration between "
+            "runner steps; inject dependencies explicitly instead."
+        ),
+        source="shadow",
+    )
+
+    assert out.startswith("ok slug=inject-test-configuration-explicitly")
+    assert "reconciliation=module-globals-for-test-configuration" in out
+    assert "review=patch_or_cross_link" in out
+    assert pkg["lessons"].count_lessons() == 2
+    row = pkg["db"].get_db().execute(
+        "SELECT target, summary FROM events WHERE kind='lesson_reconciliation'"
+    ).fetchone()
+    assert row["target"] == "module-globals-for-test-configuration"
+    assert "new=inject-test-configuration-explicitly" in row["summary"]
+    assert "reason=absolute_directive" in row["summary"]
+
+
+def test_new_debunk_flags_older_permissive_lesson_for_reconciliation(
+    tmp_path, monkeypatch,
+):
+    pkg = _bootstrap(tmp_path, monkeypatch, write_origin="shadow_review")
+    la = _tool(pkg, "lesson_append")
+
+    la(
+        title="shared runner environment state",
+        body=(
+            "It is safe to keep shared runner environment state throughout "
+            "a test workflow."
+        ),
+        source="shadow",
+    )
+
+    out = la(
+        title="shared runner environment state is unreliable",
+        body=(
+            "Keeping shared runner environment state is unreliable; pass the "
+            "environment to each command instead."
+        ),
+        source="shadow",
+    )
+
+    assert "reconciliation=shared-runner-environment-state" in out
+    row = pkg["db"].get_db().execute(
+        "SELECT summary FROM events WHERE kind='lesson_reconciliation'"
+    ).fetchone()
+    assert "reason=debunk" in row["summary"]
+
+
 def test_shadow_lesson_append_semantic_borderline_surfaces_duplicate(
     tmp_path, monkeypatch,
 ):

{threadkeeper-0.17.3 → threadkeeper-0.17.5}/tests/test_skill_use_parser.py

@@ -182,11 +182,12 @@ def test_ingest_file_bumps_skill_usage(tmp_path, monkeypatch):
     conn.commit()
     assert added == 1
     row = conn.execute(
-        "SELECT use_count, last_used_at, created_by_origin "
+        "SELECT use_count, foreground_use_count, last_used_at, created_by_origin "
         "FROM skill_usage WHERE name='swift-ios'"
     ).fetchone()
     assert row is not None
     assert row["use_count"] == 1
+    assert row["foreground_use_count"] == 1
     assert row["last_used_at"] is not None
     assert row["created_by_origin"] == "foreground"
 

{threadkeeper-0.17.3 → threadkeeper-0.17.5}/tests/test_skills.py

@@ -466,6 +466,42 @@ def test_skill_record_bumps_counters(skills_pkg):
     assert r["last_viewed_at"] is not None
 
 
+def test_skill_list_records_views_for_returned_skills(skills_pkg):
+    _seed_skill(skills_pkg, name="listed-active")
+    _seed_skill(skills_pkg, name="listed-archived")
+    conn = skills_pkg["db"].get_db()
+    conn.execute(
+        "UPDATE skill_usage SET state='archived' WHERE name='listed-archived'"
+    )
+    conn.commit()
+
+    listed = _tool(skills_pkg, "skill_list")
+    rendered = listed()
+    assert "listed-active" in rendered
+    assert "views=1" in rendered
+    rows = {
+        row["name"]: row
+        for row in conn.execute(
+            "SELECT name, view_count, last_viewed_at FROM skill_usage "
+            "WHERE name IN ('listed-active', 'listed-archived')"
+        ).fetchall()
+    }
+    assert rows["listed-active"]["view_count"] == 1
+    assert rows["listed-active"]["last_viewed_at"] is not None
+    assert rows["listed-archived"]["view_count"] == 0
+
+    assert "listed-archived" in listed(include_archived=True)
+    rows = {
+        row["name"]: row
+        for row in conn.execute(
+            "SELECT name, view_count FROM skill_usage "
+            "WHERE name IN ('listed-active', 'listed-archived')"
+        ).fetchall()
+    }
+    assert rows["listed-active"]["view_count"] == 2
+    assert rows["listed-archived"]["view_count"] == 1
+
+
 def test_skill_list_omits_archived_by_default(skills_pkg):
     _seed_skill(skills_pkg, name="alive")
     _seed_skill(skills_pkg, name="ghost")

{threadkeeper-0.17.3 → threadkeeper-0.17.5}/tests/test_spawn_slim.py

@@ -171,7 +171,7 @@ def test_visible_command_script_is_owner_only(mp_with_cid, monkeypatch):
     monkeypatch.setattr(spawn_mod.subprocess, "Popen", _FakePopen)
 
     spawn_fn = pkg["mcp"]._tool_manager._tools["spawn"].fn
-    out = spawn_fn(prompt="do a thing", visible=True)
+    out = spawn_fn(prompt="do a thing", cwd=str(pkg["tmp"]), visible=True)
     assert out.startswith("ok task="), out
 
     cmd_files = list(spawn_mod.TASK_LOG_DIR.glob("*.command"))
@@ -197,7 +197,12 @@ def test_headless_log_file_is_owner_only(mp_with_cid, monkeypatch):
     monkeypatch.setattr(spawn_mod.subprocess, "Popen", _FakePopen)
 
     spawn_fn = pkg["mcp"]._tool_manager._tools["spawn"].fn
-    out = spawn_fn(prompt="do a thing", visible=False, capture_output=True)
+    out = spawn_fn(
+        prompt="do a thing",
+        cwd=str(pkg["tmp"]),
+        visible=False,
+        capture_output=True,
+    )
     assert out.startswith("ok task="), out
 
     log_files = list(spawn_mod.TASK_LOG_DIR.glob("*.log"))

threadkeeper-0.17.5/tests/test_spawn_worktree_isolation.py

@@ -0,0 +1,112 @@
+"""Git worktree isolation on the shared spawn path."""
+from __future__ import annotations
+
+import subprocess
+from pathlib import Path
+
+
+_FAKE_CID = "aaaa0000-bbbb-1111-cccc-222233334444"
+
+
+def _git(repo: Path, *args: str) -> str:
+    proc = subprocess.run(
+        ["git", "-C", str(repo), *args],
+        text=True,
+        capture_output=True,
+        check=True,
+    )
+    return proc.stdout.strip()
+
+
+def _init_repo(tmp_path: Path) -> Path:
+    repo = tmp_path / "repo"
+    repo.mkdir()
+    _git(repo, "init", "-b", "main")
+    _git(repo, "config", "user.email", "test@example.com")
+    _git(repo, "config", "user.name", "Test User")
+    (repo / "tracked.txt").write_text("base\n", encoding="utf-8")
+    _git(repo, "add", "tracked.txt")
+    _git(repo, "commit", "-m", "base")
+    return repo
+
+
+def _configure_spawn(monkeypatch, pkg):
+    import threadkeeper.identity as identity
+    import threadkeeper.spawn_config as spawn_config
+    import threadkeeper.tools.spawn as spawn_mod
+
+    monkeypatch.setattr(spawn_mod, "_claude_bin", lambda: "/bin/true")
+    monkeypatch.setattr(identity, "_active_cli", "claude")
+    monkeypatch.setattr(
+        spawn_config, "resolve_agent", lambda role, active_cli=None: "claude"
+    )
+    monkeypatch.setattr(spawn_config, "resolve_model", lambda cli, role="": "")
+    return spawn_mod
+
+
+def test_git_spawns_get_distinct_branch_worktrees(mp_with_cid, monkeypatch):
+    pkg = mp_with_cid(_FAKE_CID)
+    repo = _init_repo(pkg["tmp"])
+    spawn_mod = _configure_spawn(monkeypatch, pkg)
+    child_cwds: list[Path] = []
+
+    class _FakePopen:
+        def __init__(self, _args, **kwargs):
+            child_cwds.append(Path(kwargs["cwd"]))
+            self.pid = 4200 + len(child_cwds)
+
+    monkeypatch.setattr(spawn_mod.subprocess, "Popen", _FakePopen)
+
+    first = spawn_mod.spawn(
+        prompt="first child", cwd=str(repo), visible=False, capture_output=False
+    )
+    second = spawn_mod.spawn(
+        prompt="second child", cwd=str(repo), visible=False, capture_output=False
+    )
+
+    assert first.startswith("ok task="), first
+    assert second.startswith("ok task="), second
+    assert len(child_cwds) == 2
+    assert child_cwds[0] != child_cwds[1]
+    assert all(path != repo and path.is_dir() for path in child_cwds)
+    roots = [
+        spawn_mod._git_result(["rev-parse", "--show-toplevel"], path)[0]
+        for path in child_cwds
+    ]
+    assert roots == [str(path) for path in child_cwds]
+    branches = [
+        spawn_mod._git_result(["branch", "--show-current"], path)[0]
+        for path in child_cwds
+    ]
+    assert len(set(branches)) == 2
+    assert all(branch.startswith("threadkeeper/spawn-tk_") for branch in branches)
+    assert spawn_mod._git_result(
+        ["status", "--porcelain", "--untracked-files=no"], repo
+    )[0] == ""
+
+
+def test_dirty_git_checkout_is_refused_before_child_launch(
+    mp_with_cid, monkeypatch,
+):
+    pkg = mp_with_cid(_FAKE_CID)
+    repo = _init_repo(pkg["tmp"])
+    spawn_mod = _configure_spawn(monkeypatch, pkg)
+    (repo / "tracked.txt").write_text("uncommitted\n", encoding="utf-8")
+
+    def _unexpected_launch(*_args, **_kwargs):
+        raise AssertionError("dirty checkout must be rejected before Popen")
+
+    monkeypatch.setattr(spawn_mod.subprocess, "Popen", _unexpected_launch)
+
+    out = spawn_mod.spawn(
+        prompt="must not launch", cwd=str(repo), visible=False, capture_output=False
+    )
+
+    assert out == "ERR spawn_dirty_worktree mode=git"
+    worktrees, err = spawn_mod._git_result(
+        ["worktree", "list", "--porcelain"], repo
+    )
+    assert not err
+    assert worktrees.count("worktree ") == 1
+    conn = pkg["db"].get_db()
+    assert conn.execute("SELECT COUNT(*) FROM tasks").fetchone()[0] == 0

{threadkeeper-0.17.3 → threadkeeper-0.17.5}/tests/test_tool_annotations.py

@@ -33,7 +33,7 @@ READ_TOOLS = {
     "memory_guard_status", "mp_dashboard", "mp_health", "neighbors", "peers",
     "pending_distillates", "pickup_candidates", "reliability_for",
     "review_candidates", "run_probe", "search", "shadow_review_status",
-    "skill_list", "skill_validate", "spawn_budget_status", "spawn_status",
+    "skill_validate", "spawn_budget_status", "spawn_status",
     "sync_peers", "sync_status", "task_logs",
     "task_thread", "tasks", "weak_spots", "whoami",
 }
@@ -65,7 +65,7 @@ WRITE_TOOLS = {
     "open_dialog_window", "open_thread", "presence", "record_attempt",
     "register_concept", "register_probe", "reject_candidate", "release_pickup",
     "respond", "review_thread", "search_via_parent", "session_end",
-    "shadow_review_run", "skill_record", "spawn", "spawn_budget_set",
+    "shadow_review_run", "skill_list", "skill_record", "spawn", "spawn_budget_set",
     "style_set", "sync_now", "tag_signal", "tournament", "validate_threads",
     "verbatim_user", "vote_distill", "wait", "whisper",
 }

{threadkeeper-0.17.3 → threadkeeper-0.17.5}/threadkeeper/curator.py

@@ -248,10 +248,11 @@ promotion and linking plan in REPORT.md for a foreground human instead.
   superseded by a newer entry, or a **FALSE POSITIVE** (auto-created
   by the background-review loop but never validated by actual use).
   Specifically flag as PRUNE:
-    • origin=background_review AND use_count=0 AND patches=0 AND
-      created >14 days ago → strong false-positive signal: nobody ever
-      consulted it, and the agent that created it never came back to
-      refine it.
+    • origin=background_review AND fg_uses=0 AND created >14 days ago
+      → strong false-positive signal: no foreground user or agent ever
+      consulted it. `maintenance_patches` count automated or other maintenance
+      writes; they are not foreground consultation and never reset this
+      eligibility signal.
     • SKILL_OUTCOME signals (in the events table) marking the skill
       as 'wrong' more often than 'helped' → user-judgment override.
   Format:

{threadkeeper-0.17.3 → threadkeeper-0.17.5}/threadkeeper/skill_audit.py

@@ -18,6 +18,7 @@ import os
 from pathlib import Path
 import re
 import sqlite3
+import time
 from typing import Iterable
 
 import yaml
@@ -245,7 +246,8 @@ def _telemetry_rows(conn: sqlite3.Connection, include_archived: bool) -> dict[st
         rows = conn.execute(
             "SELECT name, created_at, created_by_origin, last_used_at, "
             "last_viewed_at, last_patched_at, use_count, view_count, "
-            "patch_count, pinned, state, tier FROM skill_usage" + where
+            "patch_count, foreground_use_count, pinned, state, tier "
+            "FROM skill_usage" + where
             + " ORDER BY name"
         ).fetchall()
     except sqlite3.OperationalError:
@@ -327,7 +329,7 @@ def _record_for(
             for key in (
                 "created_at", "last_used_at", "last_viewed_at",
                 "last_patched_at", "use_count", "view_count", "patch_count",
-                "pinned",
+                "foreground_use_count", "pinned",
             )
         },
         "source_path": str(source) if source else None,
@@ -533,9 +535,20 @@ def format_skill_checklist(manifest: dict) -> str:
     for index, record in enumerate(manifest["skills"], start=1):
         flags = ",".join(record["findings"]) or "clean"
         protected = " [PROTECTED]" if record["protected"] else ""
+        telemetry = record["telemetry"]
+        created_at = int(telemetry.get("created_at") or 0)
+        created_age = (
+            max(0, int(time.time()) - created_at) // 86400
+            if created_at else "?"
+        )
         lines.append(
             f"{index}. SKILL {record['name']}{protected} "
             f"state={record['state']} origin={record['origin']} "
+            f"fg_uses={telemetry.get('foreground_use_count') or 0} "
+            f"uses={telemetry.get('use_count') or 0} "
+            f"views={telemetry.get('view_count') or 0} "
+            f"maintenance_patches={telemetry.get('patch_count') or 0} "
+            f"created={created_age}d_ago "
             f"source_kind={record['source_kind']} "
             f"source={record['source_path'] or '-'} findings={flags}"
         )