Skip to content

richfrem/agent-plugins-skills / plugins/agent-agentic-os/.apm/skills/running-control-plane

running-control-plane

Flagged

CRITICAL INTAKE GATEWAY: use at the start of any non-trivial engineering task, feature, refactor, multi-file bugfix, work package or new idea, including requests to explore, brainstorm, build, fix or change something, before planning or code changes. Enforces read-only discovery, 1-3 structured questions with defaults, control-plane registration and the immutable four-pillar TASK_SPEC.md. Also runs the rest of the control plane: health ("run health check", "check os metrics", "system monitor", event bus, locks, memory, "is my signing identity ready" status check), transition simulation ("dry run transition", "simulate transition", "check edge X -> Y"), worktree selection, and gating on/off ("disable the control plane", "turn off the push guard", "stop gating my commits"). Not for project setup or key creation (use setting-up-agentic-os) or improving skills (use improving-skills-in-lab).

FileKindSize
SKILL.mdskill md5.4 KB
evals/evals.jsonconfig8.3 KB
references/acceptance-criteria.mdmarkdown4.0 KB
references/agentic-os-skill-map.mdmarkdown2.3 KB
references/architecture/architecture.mdmarkdown2.4 KB
references/architecture/context-folder-patterns.mdmarkdown3.3 KB
references/architecture/vision.mdmarkdown56.6 KB
references/cheap-agent-transition-simulation.mdmarkdown6.1 KB
references/control-plane-architecture.mdmarkdown9.0 KB
references/control-plane-rebuild-recovery.mdmarkdown6.2 KB
references/control-plane-simulation-protocol.mdmarkdown5.7 KB
references/diagrams/agentic-os-memory-subsystem.mmdother1.4 KB
references/diagrams/architecture-overview.mmdother3.1 KB
references/diagrams/control-plane-architecture.mermaidother6.3 KB
references/diagrams/control-plane-lifecycle-hardened-with-ciba-rar.mermaidother4.5 KB
references/diagrams/control-plane-pipeline-happy-path.mermaidother5.0 KB
references/diagrams/control-plane-pipeline.mermaidother9.3 KB
references/diagrams/event-bus-architecture.mmdother2.4 KB
references/diagrams/increment-b-human-only-transition-ssh-signing.mermaidother5.3 KB
references/edge-matrix.mdmarkdown13.3 KB
references/fallback-tree.mdmarkdown2.9 KB
references/health-detailed-reference.mdmarkdown7.1 KB
references/healthy-transcript.mdmarkdown3.8 KB
references/implementation-ledger-contract.mdmarkdown851 B
references/intake-detailed-reference.mdmarkdown3.1 KB
references/modes/health.mdmarkdown3.4 KB
references/modes/intake.mdmarkdown3.8 KB
references/modes/mode.mdmarkdown5.8 KB
references/modes/simulator.mdmarkdown6.2 KB
references/modes/worktree.mdmarkdown2.9 KB
references/multi-round-external-review-protocol.mdmarkdown2.6 KB
references/worktree-reconciliation-and-multi-worktree-practices.mdmarkdown5.8 KB
requirements-dev.inother741 B
requirements-dev.txtmarkdown603 B
requirements.inother196 B
requirements.txtmanifest202 B
scripts/agent_control.pyscript97.7 KB
scripts/audit_map_debt.pyscript6.1 KB
scripts/capability_probe.pyscript6.4 KB
scripts/check_plan_links.pyscript1.8 KB
scripts/control_plane/__init__.pyscript842 B
scripts/control_plane/adapters.pyscript144.9 KB
scripts/control_plane/approver_policy.pyscript20.0 KB
scripts/control_plane/baseline_transition_report.pyscript4.0 KB
scripts/control_plane/constants.pyscript13.5 KB
scripts/control_plane/coordinator.pyscript57.3 KB
scripts/control_plane/edge_matrix.pyscript3.1 KB
scripts/control_plane/gate1_approval.pyscript10.7 KB
scripts/control_plane/gate_evidence.pyscript9.9 KB
scripts/control_plane/identity_layout.pyscript2.9 KB
scripts/control_plane/identity_setup.pyscript11.0 KB
scripts/control_plane/implementation.pyscript3.7 KB
scripts/control_plane/implementation_loop.pyscript11.3 KB
scripts/control_plane/inspection.pyscript3.9 KB
scripts/control_plane/installation_probe.pyscript5.7 KB
scripts/control_plane/isolation_check.pyscript14.0 KB
scripts/control_plane/measurement.pyscript39.1 KB
scripts/control_plane/pipeline_simulator.pyscript30.0 KB
scripts/control_plane/policy.pyscript32.5 KB
scripts/control_plane/ports.pyscript20.3 KB
scripts/control_plane/proof_edges.pyscript4.6 KB
scripts/control_plane/proof_policy.pyscript2.2 KB
scripts/control_plane/receipt_provenance.pyscript4.7 KB
scripts/control_plane/registry.pyscript32.9 KB
scripts/control_plane/review_options.pyscript8.2 KB
scripts/control_plane/review_selection.pyscript3.2 KB
scripts/control_plane/run_transition_simulation.pyscript12.0 KB
scripts/control_plane/signing_selftest.pyscript6.8 KB
scripts/control_plane/simulation_identity.pyscript10.4 KB
scripts/control_plane/snapshot.pyscript10.8 KB
scripts/control_plane/ssh_signing.pyscript21.8 KB
scripts/control_plane/state_machine.pyscript5.8 KB
scripts/control_plane/transition_request.pyscript19.5 KB
scripts/control_plane/transition_simulation_cases.pyscript24.6 KB
scripts/control_plane/transition_templates.yamlconfig159.1 KB
scripts/control_plane/tty_signer.pyscript3.0 KB
scripts/control_plane/wrappers/__init__.pyscript24 B
scripts/control_plane/wrappers/record_interview_question.pyscript8.0 KB
scripts/control_plane/wrappers/record_retrospective.pyscript2.3 KB
scripts/control_plane/wrappers/run_exit_verification.pyscript6.4 KB
scripts/control_plane/wrappers/run_verify_exit_bundle.pyscript5.4 KB
scripts/control_plane/wrappers/write_plan_document.pyscript9.6 KB
scripts/control_plane_hooks.pyscript10.5 KB
scripts/control_plane_mode.pyscript12.0 KB
scripts/distill_playbook.pyexecutablescript9.9 KB
scripts/evolution_state.pyscript29.4 KB
scripts/export_upstream_pr.pyscript4.4 KB
scripts/interview_spec_engine.pyscript9.1 KB
scripts/kernel.pyscript14.6 KB
scripts/pre-commit-evolution-guardexecutablescript3.7 KB
scripts/pre-commit-pipeline-guardexecutablescript13.6 KB
scripts/pre-push-review-guardexecutablescript10.5 KB
scripts/record_trace.pyscript7.2 KB
scripts/smoke_test.pyexecutablescript22.6 KB
scripts/test_capability_probe.pyscript3.9 KB
scripts/test_worktree_manager.pyscript2.8 KB
scripts/verify_evolution_receipt.pyscript7.5 KB
scripts/verify_gate_evidence.pyscript1.6 KB
scripts/worktree_manager.pyscript3.0 KB
tests/conftest.pyscript7.7 KB
tests/helpers/__init__.pyscript0 B
tests/helpers/control_plane_fixtures.pyscript2.6 KB
tests/helpers/control_plane_repo.pyscript4.0 KB
tests/helpers/gate1_fixtures.pyscript5.8 KB
tests/helpers/human_signer.pyscript7.3 KB
tests/helpers/implementation_ledger.pyscript1.1 KB
tests/interview_helpers.pyscript5.2 KB
tests/test_actionable_rollback.pyscript2.2 KB
tests/test_agent_control.pyscript190.6 KB
tests/test_agent_control_gate_characterization.pyscript14.7 KB
tests/test_approve_transition.pyscript10.5 KB
tests/test_approver_identity_guidance.pyscript3.4 KB
tests/test_approver_isolation.pyscript12.3 KB
tests/test_audit_map_debt.pyscript4.7 KB
tests/test_authorized_actor_enforcement.pyscript22.9 KB
tests/test_background_document_priority.pyscript924 B
tests/test_check_plan_links.pyscript1.1 KB
tests/test_content_snapshot.pyscript11.8 KB
tests/test_control_plane_architecture_diagram_contract.pyscript9.0 KB
tests/test_control_plane_architecture_overview_contract.pyscript2.1 KB
tests/test_control_plane_critic_review.pyscript3.1 KB
tests/test_control_plane_crypto_adapter.pyscript5.0 KB
tests/test_control_plane_delegation_contract.pyscript5.7 KB
tests/test_control_plane_facade_composition.pyscript15.9 KB
tests/test_control_plane_filesystem_adapter.pyscript4.9 KB
tests/test_control_plane_hooks.pyscript7.3 KB
tests/test_control_plane_interview_guidance.pyscript3.8 KB
tests/test_control_plane_measurement_contract.pyscript28.0 KB
tests/test_control_plane_mode.pyscript7.5 KB
tests/test_control_plane_mode_guards.pyscript3.5 KB
tests/test_control_plane_model_catalog_adapter.pyscript9.2 KB
tests/test_control_plane_pipeline_diagram_contract.pyscript2.3 KB
tests/test_control_plane_pipeline_simulator.pyscript7.5 KB
tests/test_control_plane_policy.pyscript13.0 KB
tests/test_control_plane_ports.pyscript3.2 KB
tests/test_control_plane_reset_transition.pyscript13.6 KB
tests/test_control_plane_schema_rebuild_atomicity.pyscript20.0 KB
tests/test_control_plane_simulation_protocol_contract.pyscript959 B
tests/test_control_plane_sqlite_persistence_adapter.pyscript5.5 KB
tests/test_control_plane_state_machine.pyscript15.2 KB
tests/test_control_plane_trigger_enforcement.pyscript14.6 KB
tests/test_control_plane_worktree_sharing.pyscript4.5 KB
tests/test_domain_namespaces.pyscript6.7 KB
tests/test_done_closure_proof.pyscript6.9 KB
tests/test_draft_plan_interactive_outline_gap.pyscript2.2 KB
tests/test_dual_identity_onboarding.pyscript7.3 KB
tests/test_edge_matrix.pyscript3.2 KB
tests/test_ensure_schema_fastpath.pyscript4.4 KB
tests/test_evolution_guards.pyscript14.9 KB
tests/test_evolution_scripts.pyscript55.3 KB
tests/test_gate1_guidance.pyscript1.8 KB
tests/test_gate3_code_acceptance.pyscript13.5 KB
tests/test_graph_state_machine.pyscript16.0 KB
tests/test_guidance_readiness.pyscript2.2 KB
tests/test_health_check_signing_status.pyscript3.5 KB
tests/test_human_decision_trigger_enforcement.pyscript37.3 KB
tests/test_human_only_wiring.pyscript22.3 KB
tests/test_human_signer_isolation.pyscript4.0 KB
tests/test_identity_verification_readiness.pyscript5.8 KB
tests/test_implementation_ledger.pyscript3.4 KB
tests/test_implementation_loop.pyscript6.9 KB
tests/test_implementation_runtime_bridge.pyscript2.6 KB
tests/test_init_agentic_os_scaffolding.pyscript10.0 KB
tests/test_init_respects_control_plane_mode.pyscript4.3 KB
tests/test_inspect_verbs.pyscript3.6 KB
tests/test_installation_probe.pyscript3.1 KB
tests/test_intake_scenarios.pyscript7.2 KB
tests/test_interview_plan_outline.pyscript2.8 KB
tests/test_isolation_check.pyscript12.5 KB
tests/test_isolation_setup_docs.pyscript2.7 KB
tests/test_kernel_security.pyscript4.0 KB
tests/test_legacy_input_fallback.pyscript6.0 KB
tests/test_list_review_options.pyscript3.1 KB
tests/test_multi_agent_bundle_gate.pyscript5.5 KB
tests/test_one_approver_per_pipeline.pyscript15.8 KB
tests/test_os_init_dual_identity.pyscript3.9 KB
tests/test_os_init_identity_bootstrap.pyscript8.8 KB
tests/test_os_init_identity_status.pyscript3.9 KB
tests/test_os_init_single_instruction_file.pyscript7.3 KB
tests/test_p00_live_baseline.pyscript10.2 KB
tests/test_p01_intake_persistence.pyscript6.7 KB
tests/test_post_run_metrics_protocol.pyscript3.3 KB
tests/test_pre_commit_pipeline_guard.pyscript29.1 KB
tests/test_pre_push_review_guard.pyscript5.7 KB
tests/test_receipt_provenance.pyscript6.6 KB
tests/test_retrospective_pipeline.pyscript5.3 KB
tests/test_review_option_menus.pyscript6.6 KB
tests/test_review_selection.pyscript8.2 KB
tests/test_round3_fixes.pyscript8.3 KB
tests/test_rules_compliance.pyscript1.3 KB
tests/test_run_transition_simulation_formatting.pyscript1.7 KB
tests/test_run_verify_exit_bundle.pyscript10.2 KB
tests/test_setup_ciba_identity.pyscript11.2 KB
tests/test_signed_approval_human_receipt.pyscript3.9 KB
tests/test_signing_mechanics_selftest.pyscript6.9 KB
tests/test_signing_skill_selfcontained.pyscript3.4 KB
tests/test_skip_receipt_guidance.pyscript2.7 KB
tests/test_ssh_signing.pyscript23.9 KB
tests/test_strategy_artifacts.pyscript21.8 KB
tests/test_transition_answer_normalization.pyscript1.1 KB

scripts/control_plane/run_transition_simulation.py

View on GitHub
#!/usr/bin/env python3
"""
run_transition_simulation.py
=============================

Purpose:
    Manual, opt-in cheap-agent dry-run for one specific transition edge (or all
    edges). Run this whenever you change a transition's YAML guidance/questions
    or the coordinator's Python logic, targeted at just the edge you changed --
    not as part of the normal pytest suite (LLM calls cost real time/money; see
    references/simulator/cheap-agent-transition-simulation.md).

    Grades each case against the 4 fixed criteria (transition_simulation_cases.
    grade_reply) plus the guidance-compliance answer match, using the `claude`
    CLI directly (no API key/SDK needed -- confirmed working).

Key Input Dependencies:
    - control_plane.registry.TransitionRegistry (transition_templates.yaml)
    - the `claude` CLI binary on PATH, with --model haiku support
    - transition_simulation_cases.py (case generation + grading)

Usage:
    python3 run_transition_simulation.py --from INTAKE --to INTERVIEW
    python3 run_transition_simulation.py --from INTAKE --to INTERVIEW --condition HUMAN_REJECTS
    python3 run_transition_simulation.py --all   # full 151-case suite, ~25 min
    python3 run_transition_simulation.py --behavior --from INTAKE --to INTERVIEW --print-prompt   # no model call
    python3 run_transition_simulation.py --behavior --all --iteration 1 --log iterations.jsonl --note baseline

Index:
    - run_case() -- runs one case through the claude CLI and grades it
    - format_actor_classification_line() -- pure formatter for a case's edge
      authorized_actor + (for adversarial cases) the expected denial reason
    - run_behavior_case() -- one BEHAVIOR run (WHO runs it, command, message to the human)
    - run_behavior() -- BEHAVIOR mode driver: one edge, or --all edges, logged per iteration
    - main() -- CLI entry point
"""

import argparse
import concurrent.futures
import subprocess
import sys
import time
from pathlib import Path
from typing import List

sys.path.insert(0, str(Path(__file__).resolve().parent.parent))

from control_plane.edge_matrix import build_edge_matrix
from control_plane.registry import TransitionRegistry, TransitionTemplate
from control_plane.transition_simulation_cases import (
    SimulationCase,
    append_iteration_log,
    build_agent_spoof_adversarial_cases,
    build_behavior_prompt,
    grade_behavior_reply,
    build_dry_run_prompt,
    build_simulation_cases,
    grade_reply,
)


import shutil
from typing import Optional

SUPPORTED_BACKENDS = ("auto", "agy", "claude", "codex", "copilot")


def resolve_backend(backend_choice: str = "auto") -> str:
    """Resolve which CLI binary to dispatch simulation runs to."""
    if backend_choice in ("agy", "claude", "codex", "copilot"):
        return backend_choice
    for b in ("agy", "claude", "codex", "copilot"):
        if shutil.which(b):
            return b
    return "agy"


def build_cli_cmd(
    backend: str,
    prompt: str,
    model: Optional[str] = None,
    effort: Optional[str] = None,
    disallow_tools: bool = True,
) -> list:
    """Construct non-interactive execution command for the target harness CLI."""
    if backend == "agy":
        cmd = ["agy", "-p", prompt]
        if model:
            cmd.extend(["--model", model])
        if effort:
            cmd.extend(["--effort", effort])
        return cmd
    elif backend == "claude":
        cmd = ["claude", "-p", prompt]
        if disallow_tools:
            cmd.extend(["--disallowedTools", "Bash,Edit,Write,Read,Grep,Glob"])
        if model:
            cmd.extend(["--model", model])
        if effort:
            cmd.extend(["--effort", effort])
        return cmd
    elif backend == "copilot":
        cmd = ["copilot", "-p", prompt, "-s"]
        if model:
            cmd.extend(["--model", model])
        return cmd
    elif backend == "codex":
        cmd = ["codex", "exec", prompt]
        if model:
            cmd.extend(["-m", model])
        return cmd
    else:
        cmd = [backend, "-p", prompt]
        if model:
            cmd.extend(["--model", model])
        return cmd


def format_actor_classification_line(case: SimulationCase, template: TransitionTemplate) -> str:
    """Pure formatter: shows the edge's authorized_actor classification, and for
    an adversarial (AGENT_SPOOF_DENIED) case, the expected denial reason."""
    line = f"  authorized_actor: {template.authorized_actor}"
    if case.condition == "AGENT_SPOOF_DENIED":
        line += " -- expected: DENIED (human_only edge, non-interactive agent actor)"
    return line


def run_case(case: SimulationCase, purpose: str, next_steps_hint: str, backend: str = "auto", model: Optional[str] = None) -> dict:
    prompt = build_dry_run_prompt(case, purpose, next_steps_hint)
    start = time.monotonic()
    active_backend = resolve_backend(backend)
    cmd = build_cli_cmd(active_backend, prompt, model=model or ("haiku" if active_backend == "claude" else None))
    proc = subprocess.run(
        cmd,
        capture_output=True, text=True, timeout=60,
    )
    elapsed = time.monotonic() - start
    result = grade_reply(case, proc.stdout)
    result["elapsed_seconds"] = round(elapsed, 1)
    result["backend"] = active_backend
    return result


def run_behavior_case(row: dict, registry: TransitionRegistry, model: Optional[str] = None, effort: Optional[str] = None, backend: str = "auto") -> dict:
    """Run one BEHAVIOR case through the CLI (no tools) and grade it deterministically."""
    prompt = build_behavior_prompt(row, registry)
    start = time.monotonic()
    active_backend = resolve_backend(backend)
    cmd = build_cli_cmd(active_backend, prompt, model=model, effort=effort, disallow_tools=True)
    proc = subprocess.run(
        cmd,
        capture_output=True, text=True, timeout=240,
    )
    result = grade_behavior_reply(row, proc.stdout)
    result["elapsed_seconds"] = round(time.monotonic() - start, 1)
    result["backend"] = active_backend
    return result


def run_behavior(args, registry: TransitionRegistry) -> int:
    """BEHAVIOR mode: judge whether the guidance tells an agent who runs each edge and what to say to the human."""
    rows = build_edge_matrix(registry)
    if not args.all:
        if not args.from_state or not args.to_state:
            print("--behavior needs --from and --to, or --all")
            return 2
        rows = [r for r in rows if r["from_state"] == args.from_state and r["to_state"] == args.to_state]
        if not rows:
            print(f"No edge {args.from_state} -> {args.to_state} found in the registry.")
            return 1
    if args.print_prompt:
        for row in rows:
            print(build_behavior_prompt(row, registry))
        return 0
    log_path = Path(args.log) if args.log else None
    failures = 0
    with concurrent.futures.ThreadPoolExecutor(max_workers=args.workers) as pool:
        futures = {pool.submit(run_behavior_case, row, registry, args.model, args.effort, args.backend): row for row in rows}
        for future in concurrent.futures.as_completed(futures):
            row = futures[future]
            try:
                result = future.result()
            except Exception as error:  # a model/timeout failure is a FAIL for that edge, not a crash
                result = {"transition_id": row["transition_id"], "criteria": {}, "overall_pass": False,
                          "raw_reply": f"RUNNER ERROR: {error}", "elapsed_seconds": 0}
            failures += 0 if result["overall_pass"] else 1
            print(f"[{'PASS' if result['overall_pass'] else 'FAIL'}] {row['from_state']}->{row['to_state']} "
                  f"({row['run_by']}) {result['elapsed_seconds']}s "
                  + " ".join(k for k, v in result["criteria"].items() if not v))
            if log_path:
                append_iteration_log(log_path, iteration=args.iteration, row=row, result=result, change_note=args.note)
    print(f"\n{len(rows) - failures}/{len(rows)} edges passed (iteration {args.iteration}).")
    return 0 if failures == 0 else 1


def print_result(result: dict, actor_line: str = "") -> None:
    status = "PASS" if result["overall_pass"] else "FAIL"
    print(f"\n[{status}] {result['case_id']} ({result['elapsed_seconds']}s)")
    if actor_line:
        print(actor_line)
    for criterion, passed in result["criteria"].items():
        mark = "OK" if passed else "MISSING"
        print(f"  {criterion}: {mark}")
    guidance_mark = "OK" if result["guidance_answer_matches_expected"] else "MISMATCH"
    print(f"  guidance_compliance_answer: {guidance_mark}")
    if not result["overall_pass"]:
        print("  --- raw reply (for debugging YAML/coordinator.py) ---")
        print("  " + result["raw_reply"].replace("\n", "\n  "))


def main():
    parser = argparse.ArgumentParser(description="Cheap-agent dry-run simulation for control-plane transitions")
    parser.add_argument("--from", dest="from_state", help="Source state (omit with --all)")
    parser.add_argument("--to", dest="to_state", help="Target state (omit with --all)")
    parser.add_argument("--condition", choices=["HUMAN_APPROVES", "HUMAN_REJECTS"], default=None,
                        help="Restrict to one condition (default: both, where applicable)")
    parser.add_argument("--all", action="store_true", help="Run the full case suite (~25 min)")
    parser.add_argument("--adversarial", action="store_true",
                        help="Run only the agent-spoof adversarial matrix (one denial case per human_only edge)")
    parser.add_argument("--behavior", action="store_true",
                        help="BEHAVIOR mode: does the guidance tell the agent WHO runs the edge and what to tell the human?")
    parser.add_argument("--print-prompt", action="store_true", help="With --behavior: print the prompt, call no model")
    parser.add_argument("--iteration", type=int, default=1, help="With --behavior: iteration number recorded in the log")
    parser.add_argument("--log", default=None, help="With --behavior: JSONL file to append one row per edge")
    parser.add_argument("--note", default="", help="With --behavior: what changed before this iteration")
    parser.add_argument("--model", default=None, help="With --behavior: model for the simulated agent (default: backend default)")
    parser.add_argument("--effort", default="medium", help="With --behavior: reasoning effort for the simulated agent")
    parser.add_argument("--workers", type=int, default=4, help="With --behavior: parallel model calls")
    parser.add_argument("--backend", choices=SUPPORTED_BACKENDS, default="auto",
                        help="CLI backend to execute simulations (default: auto)")
    args = parser.parse_args()

    registry = TransitionRegistry.load_default()
    if args.behavior:
        sys.exit(run_behavior(args, registry))
    all_cases = build_agent_spoof_adversarial_cases(registry) if args.adversarial else build_simulation_cases(registry)

    if args.adversarial:
        target_cases = all_cases
        if args.from_state and args.to_state:
            target_cases = [c for c in target_cases if c.from_state == args.from_state and c.to_state == args.to_state]
    elif args.all:
        target_cases = all_cases
    else:
        if not args.from_state or not args.to_state:
            parser.error("--from and --to are required unless --all is given")
        target_cases = [
            c for c in all_cases
            if c.from_state == args.from_state and c.to_state == args.to_state
            and (args.condition is None or c.condition == args.condition)
        ]
        if not target_cases:
            print(f"No edge {args.from_state} -> {args.to_state} found in the registry.")
            sys.exit(1)

    results = []
    for case in target_cases:
        template = registry.get_template(case.from_state, case.to_state)
        result = run_case(case, template.purpose, template.next_steps_hint, backend=args.backend)
        results.append(result)
        print_result(result, format_actor_classification_line(case, template))

    passed = sum(1 for r in results if r["overall_pass"])
    print(f"\n{passed}/{len(results)} cases passed.")
    sys.exit(0 if passed == len(results) else 1)


if __name__ == "__main__":
    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 CodeCodexUnverifiedInstall
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