chore(skills): apply the 2026-10-02 review -- current CLI and evidence, merges, removals, steering names

openultrasast-scan: evidence ladder as verification.py defines it, with the levels nothing produces today; --mode prerequisites, --fail-on, recorded degradations, run artifacts, ousast mcp; retired [evidence] threshold language removed. openultrasast-triage: reasons verified against calibration.py; deterministic fusion; adjudications as labels, plane verdicts as features, rule changes through improve or a registered experiment; fix-audit merged as a fix-and-re-scan section. kiro: spec-quick and spec-batch removed; validate-gap and validate-design merged into spec-design (--gap, --review; the review gate stays); steering-custom merged into steering; core steering names overview.md, roadmap.md, safety-net.md; instrument rule in debug and verify-completion; repo gates named in validate-impl. AGENTS.md, README skills paragraph and tests/test_agent_skills.py (.agents/skills, two product skills, drift tests) updated.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo

tests/test_agent_skills.py

@@ -1,14 +1,14 @@
 from pathlib import Path
 
+SKILLS_ROOT = Path(".agents/skills")  # the plural directory OpenCode searches by default
+
 
 def test_project_agent_skills_have_required_frontmatter() -> None:
-    skills_root = Path(".agent/skills")
     # Scope to the project's own skills; third-party tooling (e.g. kiro-*) lives
     # alongside them and uses a different frontmatter convention.
-    skill_files = sorted(skills_root.glob("openultrasast-*/SKILL.md"))
+    skill_files = sorted(SKILLS_ROOT.glob("openultrasast-*/SKILL.md"))
 
     assert {path.parent.name for path in skill_files} == {
-        "openultrasast-fix-audit",
         "openultrasast-scan",
         "openultrasast-triage",
     }
@@ -19,3 +19,41 @@ def test_project_agent_skills_have_required_frontmatter() -> None:
         assert f"name: {skill_file.parent.name}" in header
         assert "description: " in header
         assert "Use when" in header
+
+
+def test_scan_skill_states_the_evidence_ladder_as_the_code_defines_it() -> None:
+    # The skill must not drift from verification.py again: every level, in the code's order, and the
+    # retired threshold language gone.
+    text = (SKILLS_ROOT / "openultrasast-scan" / "SKILL.md").read_text()
+    levels = [
+        "suspicion",
+        "static_corroboration",
+        "crash_reproduced",
+        "root_cause_explained",
+        "exploit_demonstrated",
+        "patch_validated",
+    ]
+    ladder = text[text.index("## Evidence ladder") : text.index("## Run artifacts")]
+    positions = [ladder.index(f"`{level}`") for level in levels]
+    assert positions == sorted(positions)
+    assert "configured report threshold" not in text
+    current_cli = (
+        "--mode quick|standard|deep",
+        "--fail-on",
+        "cpg_unavailable",
+        "sandbox_unavailable",
+        "report.sarif",
+        "harness.json",
+        "ousast mcp",
+    )
+    for flag in current_cli:
+        assert flag in text, flag
+
+
+def test_triage_skill_lists_the_false_positive_reasons_exactly() -> None:
+    from openultrasast.calibration import FalsePositiveReason
+
+    text = (SKILLS_ROOT / "openultrasast-triage" / "SKILL.md").read_text()
+    listed = {line.strip()[3:-1] for line in text.splitlines() if line.startswith("- `") and line.strip().endswith("`")}
+    assert listed == {reason.value for reason in FalsePositiveReason}
+    assert "patch_validated" in text and "Nothing in the tool records `patch_validated`" in text