Skip to content

matt-bat/got-skills / skills/skill-governance

skill-governance

Verified

Govern release-affecting, policy-changing, externally mutating, destructive, or otherwise high-risk work through typed effects, mandatory evidence, independent safety gates, and an explicit go/no-go decision. Do not use for ordinary answers, read-only inspection, tiny reversible edits, or a task made "multi-skill" only by optional process helpers.

FileKindSize
SKILL.mdskill md9.7 KB
fixtures/passed-artifact-evidence.jsonconfig104 B
fixtures/routing-scenarios.jsonconfig44.2 KB
references/governance-artifacts.mdmarkdown5.1 KB
references/risk-and-gates.mdmarkdown4.6 KB
requirements.txtmanifest89 B
schemas/governance-artifact.schema.jsonconfig13.6 KB
schemas/remote-configuration-policy.schema.jsonconfig4.3 KB
schemas/routing-result.schema.jsonconfig7.7 KB
schemas/task-descriptor.schema.jsonconfig13.3 KB
scripts/enforce_governance_ci.pyscript24.4 KB
scripts/generate_governance_artifact.pyscript43.4 KB
scripts/generate_routing_views.pyscript27.6 KB
scripts/governance_common.pyscript14.5 KB
scripts/record_routing_observation.pyscript9.3 KB
scripts/resolve_task_route.pyscript69.4 KB
scripts/validate_governance_artifact.pyscript39.9 KB
scripts/validate_skill_order_sync.pyscript4.0 KB
scripts/validate_skill_policy.pyscript32.3 KB
scripts/verify_remote_configuration.pyscript12.3 KB
tests/test_advanced_svg_render.pyscript5.1 KB
tests/test_conflict_matrix_integrity.pyscript2.1 KB
tests/test_default_skill_quality_gates.pyscript2.9 KB
tests/test_docs_website_navigation.pyscript2.7 KB
tests/test_enforce_governance_scope.pyscript1.7 KB
tests/test_generate_governance_startup.pyscript9.0 KB
tests/test_generate_routing_views.pyscript12.8 KB
tests/test_governance_history_and_pair_integrity.pyscript10.6 KB
tests/test_governance_integrity.pyscript55.7 KB
tests/test_new_skill_integration.pyscript8.3 KB
tests/test_project_index_integrity.pyscript6.4 KB
tests/test_remote_configuration.pyscript5.6 KB
tests/test_routing_observation.pyscript4.3 KB
tests/test_runtime_adapter.pyscript9.2 KB
tests/test_task_routing.pyscript47.5 KB
tests/test_validate_skill_order_sync.pyscript2.4 KB
tests/test_validate_skill_policy_smoke.pyscript869 B

tests/test_routing_observation.py

View on GitHub
import json
import subprocess
import sys
import tempfile
import unittest
from pathlib import Path


SCRIPT = Path(__file__).resolve().parents[1] / "scripts" / "record_routing_observation.py"


class RoutingObservationTests(unittest.TestCase):
    def run_script(self, *args: str) -> subprocess.CompletedProcess[str]:
        return subprocess.run(
            [sys.executable, "-B", str(SCRIPT), *args], text=True, capture_output=True, check=False
        )

    def test_records_only_allowed_operational_metadata_and_prunes(self) -> None:
        with tempfile.TemporaryDirectory() as temp:
            path = Path(temp) / "observations.jsonl"
            for index in range(3):
                result = self.run_script(
                    "record", "--out", str(path), "--task-class", "implement",
                    "--checkpoint", "post_diff", "--selected-skills",
                    "regression-prevention,effective-testing-methods", "--validation-outcome", "pass",
                    "--corrections", str(index), "--max-records", "2",
                )
                self.assertEqual(result.returncode, 0, result.stderr)
            records = [json.loads(line) for line in path.read_text().splitlines()]
            self.assertEqual(len(records), 2)
            self.assertEqual(records[-1]["corrections"], 2)
            forbidden = {"prompt", "source", "reasoning", "secret", "files"}
            self.assertFalse(forbidden.intersection(records[-1]))

    def test_summary_is_aggregate_only(self) -> None:
        with tempfile.TemporaryDirectory() as temp:
            path = Path(temp) / "observations.jsonl"
            recorded = self.run_script(
                "record", "--out", str(path), "--task-class", "review",
                "--checkpoint", "initial", "--validation-outcome", "not_run",
            )
            self.assertEqual(recorded.returncode, 0, recorded.stderr)
            summary = self.run_script("summary", "--out", str(path))
            self.assertEqual(summary.returncode, 0, summary.stderr)
            payload = json.loads(summary.stdout)
            self.assertEqual(payload["records"], 1)
            self.assertEqual(payload["task_classes"], {"review": 1})

    def test_rejects_negative_counts(self) -> None:
        with tempfile.TemporaryDirectory() as temp:
            result = self.run_script(
                "record", "--out", str(Path(temp) / "observations.jsonl"),
                "--task-class", "answer", "--checkpoint", "initial",
                "--validation-outcome", "pass", "--retries", "-1",
            )
            self.assertNotEqual(result.returncode, 0)
            self.assertIn("non-negative", result.stderr)

    def test_rejects_unknown_skill_names_and_oversized_retention(self) -> None:
        with tempfile.TemporaryDirectory() as temp:
            path = str(Path(temp) / "observations.jsonl")
            unknown = self.run_script(
                "record", "--out", path, "--task-class", "answer",
                "--checkpoint", "initial", "--validation-outcome", "pass",
                "--selected-skills", "invented-free-text-skill",
            )
            oversized = self.run_script(
                "record", "--out", path, "--task-class", "answer",
                "--checkpoint", "initial", "--validation-outcome", "pass",
                "--max-records", "101",
            )
            self.assertNotEqual(unknown.returncode, 0)
            self.assertIn("outside the catalog", unknown.stderr)
            self.assertNotEqual(oversized.returncode, 0)
            self.assertIn("between 1 and 100", oversized.stderr)

    def test_checkpoint_namespace_matches_task_router(self) -> None:
        with tempfile.TemporaryDirectory() as temp:
            path = str(Path(temp) / "observations.jsonl")
            accepted = self.run_script(
                "record", "--out", path, "--task-class", "operate",
                "--checkpoint", "pre_external_action", "--validation-outcome", "pass",
            )
            rejected = self.run_script(
                "record", "--out", path, "--task-class", "operate",
                "--checkpoint", "pre_external", "--validation-outcome", "pass",
            )
            self.assertEqual(accepted.returncode, 0, accepted.stderr)
            self.assertNotEqual(rejected.returncode, 0)


if __name__ == "__main__":
    unittest.main()
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall