Skip to content

richfrem/agent-plugins-skills / plugins/agent-orchestration/.apm/skills/orchestrating-agent-work

orchestrating-agent-work

Verified

Interactive orchestrator for complex engineering work. Analyzes the task, conducts a diagnostic interview to select the appropriate execution strategy (Directed Acyclic Graph versus Loop, and which Loop type), plans the artifact, and supervises execution and verification. Use for "how should I orchestrate this", "plan this workflow", "should this be a DAG or a loop", "run these jobs in parallel", "delegate this to a worker agent", or "run/resume this graph manifest". Not for single trivial edits or skill self-improvement.

FileKindSize
SKILL.mdskill md6.8 KB
assets/templates/dual-loop-meta-tasks.mdmarkdown1.6 KB
assets/templates/loop_retrospective_template.mdmarkdown1.5 KB
assets/templates/red_team_briefing_template.mdmarkdown747 B
assets/templates/scratchpad-template.mdmarkdown991 B
assets/templates/strategy-packet-template.mdmarkdown1.2 KB
assets/templates/workflow-retrospective-template.mdmarkdown1.3 KB
evals/evals.jsonconfig7.0 KB
references/PATTERN_GUIDE.mdmarkdown6.2 KB
references/acceptance-criteria.mdmarkdown6.8 KB
references/agentic-os-reuse-map.mdmarkdown2.5 KB
references/bot-delegation-patterns.mdmarkdown5.2 KB
references/cheapest_models.jsonconfig845 B
references/cheapest_models.mdmarkdown1.1 KB
references/cli-agent-executor.mdmarkdown3.5 KB
references/delegated-dag-refactoring-playbook.mdmarkdown5.5 KB
references/diagrams/agent_swarm.mmdother1.8 KB
references/diagrams/dual_loop_architecture.mmdother1.4 KB
references/diagrams/graph-planner-flow.mmdother540 B
references/diagrams/graph_execution_state_machine.mmdother823 B
references/diagrams/orchestrating_agent_work_architecture.mmdother4.5 KB
references/dispatch-preflight.mdmarkdown2.1 KB
references/fallback-tree.mdmarkdown9.7 KB
references/graph-execution.mdmarkdown4.1 KB
references/graph-manifest-schema.jsonconfig7.0 KB
references/graph-planning.mdmarkdown3.0 KB
references/learning-loop.mdmarkdown4.9 KB
references/patterns.jsonconfig2.0 KB
references/post_run_survey.mdmarkdown1.4 KB
references/routing-and-closure.mdmarkdown2.4 KB
references/strategy-agent-swarm.mdmarkdown2.1 KB
references/strategy-dual-loop.mdmarkdown1.6 KB
references/strategy-red-team-review.mdmarkdown2.0 KB
references/strategy-selection.mdmarkdown4.0 KB
references/topology-rules.mdmarkdown6.0 KB
scripts/agent_orchestrator.pyscript7.6 KB
scripts/dispatch_guard.pyscript1.1 KB
scripts/graph_runner.pyexecutablescript36.3 KB
scripts/select_strategy.pyscript13.1 KB
scripts/swarm_run.pyscript28.0 KB
scripts/validate_manifest.pyexecutablescript19.8 KB
scripts/work_loop.pyscript28.0 KB
tests/_loop_fixtures.pyscript2.5 KB
tests/test_graph_fixes.pyscript12.6 KB
tests/test_graph_runner.pyscript30.0 KB
tests/test_isolation.pyscript3.5 KB
tests/test_loop_strategies.pyscript7.7 KB
tests/test_select_strategy.pyscript7.8 KB
tests/test_swarm_run.pyscript9.4 KB
tests/test_swarm_run_models.pyscript3.1 KB
tests/test_validate_manifest.pyscript18.1 KB
tests/test_work_loop_e2e.pyscript3.8 KB
tests/test_work_loop_hardening.pyscript27.3 KB

tests/test_isolation.py

View on GitHub
#!/usr/bin/env python3
"""
Plug-and-Play Independence & Isolation Test for agent-orchestration
===================================================================

Verifies:
1. Copy with symlinks dereferenced into an isolated temporary directory.
2. Full execution of plugin test suite in isolation (no external sibling plugins present).
3. Static grep asserting ZERO matches for banned caller-coupling terms:
   agent-agentic-os | control_plane | evolution_state | TASK_PLAN | cli-agents
   (test_isolation.py excludes itself from the banned-term grep).
"""

import sys
import os
import re
import shutil
import tempfile
import subprocess
import unittest
from pathlib import Path

PLUGIN_ROOT = Path(__file__).resolve().parent.parent


class TestPluginIsolation(unittest.TestCase):

    def setUp(self):
        self.temp_isolated_dir = tempfile.mkdtemp(prefix="isolated_orchestration_")
        self.dest_plugin = Path(self.temp_isolated_dir) / "agent-orchestration"

        # Copy plugin with symlinks dereferenced (symlinks=False copies target file content)
        shutil.copytree(PLUGIN_ROOT, self.dest_plugin, symlinks=False)

    def tearDown(self):
        shutil.rmtree(self.temp_isolated_dir, ignore_errors=True)

    def test_run_tests_in_standalone_isolation(self):
        """Run the plugin's core test suites in the isolated directory."""
        tests_to_run = [
            "tests/test_loop_strategies.py",
            "tests/test_validate_manifest.py",
            "tests/test_graph_runner.py"
        ]
        cmd = [sys.executable, "-m", "pytest"] + tests_to_run + ["-v"]
        res = subprocess.run(
            cmd,
            cwd=self.dest_plugin,
            stdout=subprocess.PIPE,
            stderr=subprocess.PIPE,
            text=True
        )
        self.assertEqual(
            res.returncode, 0,
            f"Test suite failed when running in isolated directory:\nSTDOUT:\n{res.stdout}\nSTDERR:\n{res.stderr}"
        )

    def test_static_grep_zero_caller_coupling(self):
        """Assert zero occurrences of banned caller-coupling terms in code and refactored skills."""
        banned_pattern = re.compile(
            r"agent-agentic-os|control_plane|evolution_state|TASK_PLAN|cli-agents"
        )
        violations = []

        # Scan all .py files in plugin, plus all files in refactored skills and references
        for p in self.dest_plugin.rglob("*"):
            if not p.is_file():
                continue
            # test_isolation.py excludes itself from the banned-term grep
            if p.name == "test_isolation.py":
                continue

            rel_str = str(p.relative_to(self.dest_plugin))

            is_code = (p.suffix == ".py")
            is_refactored_asset = any(part in rel_str for part in [
                "graph-execution", "graph-planner", "select-loop-strategy",
                "orchestrator", "references", "scripts"
            ])

            if is_code or is_refactored_asset:
                text = p.read_text(encoding="utf-8", errors="ignore")
                for line_num, line in enumerate(text.splitlines(), start=1):
                    match = banned_pattern.search(line)
                    if match:
                        violations.append(
                            f"{rel_str}:{line_num}: matched '{match.group(0)}' -> {line.strip()}"
                        )

        self.assertEqual(
            violations, [],
            f"Found {len(violations)} banned caller-coupling reference(s):\n" + "\n".join(violations)
        )


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: 471kUpdated 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