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

references/cheap-agent-transition-simulation.md

View on GitHub
# Cheap-Agent Transition Simulation (behavioral regression check)

## Contents

- [Purpose](#purpose)
- [Cost/Timing (measured, not estimated)](#costtiming-measured-not-estimated)
- [When to run this](#when-to-run-this)
- [How to run it](#how-to-run-it)
- [What a pass looks like](#what-a-pass-looks-like)
- [Known limitation](#known-limitation)
- [Improvement ideas (not yet implemented)](#improvement-ideas-not-yet-implemented)


## Purpose

`PipelineSimulator` (`control_plane/pipeline_simulator.py`) exercises the control
plane's Python API directly with scripted, canned answers — useful for
deterministic unit-level regression, but it never tests whether a real LLM agent
actually reads and correctly follows the printed transition guidance. This
approach closes that gap: a real, cheap model (e.g. Haiku) is given a single
fixed assignment — perform exactly one named transition (`FROM_STATE -> TO_STATE`)
on a throwaway task in a throwaway database — with no other context, and its
actual behavior is checked against what the guidance/gate contract requires.

This is a **behavioral** check (does an agent actually comply when genuinely
reading the prompts) as opposed to `PipelineSimulator`'s **structural** check
(does the state machine accept/reject the right things when a canned answer is
supplied). Run both; they catch different failure classes.

## Cost/Timing (measured, not estimated)

3 real `claude -p ... --model haiku` calls: 10.1s, 8.6s, 11.2s (~10s average).
Full case set is 151 cases (126 non-exempt edges x 2 conditions + 25
force-close-exempt edges x 1 condition each) = **~25 minutes sequential**.
LLM calls are meaningfully slower and costlier than the deterministic
`PipelineSimulator` layer (which runs in seconds with zero external calls) --
run the deterministic suite first every time; run this layer only when
specifically needed, never as a default/every-session regression.

## When to run this

- After any change to `coordinator.py`'s printed guidance text, its human
  question set, or any new mandatory gate (e.g. the guidance-compliance
  confirmation).
- After any change to `transition_templates.yaml` `next_steps_hint` /
  `human_questions` wording, to confirm the new wording is actually followable
  by an agent with no other context, not just readable by a human reviewer.
- As a periodic regression alongside the pytest suite — it is not a substitute
  for it.

## How to run it

**Mechanism (confirmed working, harness-agnostic):** both `agy` (`agy -p ... --model <cheapest-suitable-tier model>`)
and `claude` (`claude -p ... --model <cheapest-suitable-tier model>`) CLI tools support non-interactive, single-shot calls via
`-p`/`--print` and `--model`. `run_transition_simulation.py` auto-detects the available backend or accepts
`--backend {auto,agy,claude}`. That's enough to drive a cheap model directly from a plain shell or Python
script without an SDK or API key dependency:

```bash
# Auto-detects agy or claude:
python3 plugins/agent-agentic-os/skills/running-control-plane/scripts/control_plane/run_transition_simulation.py \
  --behavior --from <FROM_STATE> --to <TO_STATE>

# Or explicit backend:
python3 plugins/agent-agentic-os/skills/running-control-plane/scripts/control_plane/run_transition_simulation.py \
  --behavior --from <FROM_STATE> --to <TO_STATE> --backend agy
```

### Two layers

1. **Data-driven case generation** (`transition_simulation_cases.py`, tested
   by `test_transition_simulation_cases.py` in the normal pytest suite) —
   pure Python, builds one case per (edge, condition) pair from
   `TransitionRegistry` (YAML). Zero cost, runs every time, catches drift
   in the case data itself.
2. **Dry-run execution** (manual/opt-in, NOT part of the normal pytest suite
   — LLM calls cost real time and should only run on demand): for each case,
   build its prompt via `build_dry_run_prompt(case, template.purpose)` and run:
   ```bash
   claude -p "$(python3 -c "... print(build_dry_run_prompt(case, purpose))")" --model haiku
   ```
   The prompt explicitly instructs the model to report its **plan only** — no
   tool calls, no actual file/database mutation — so this step never touches
   real state and is safe to run against the live repo. It also picks up this
   repo's own `CLAUDE.md`/rule context automatically (confirmed in testing),
   which is representative of real agent behavior, not an isolated sandbox.
3. Compare the reply's stated answer for `guidance_compliance_confirmation`
   against `case.expected_guidance_confirmation_answer` — this is the
   pass/fail signal. A HUMAN_REJECTS case should produce a reply that does NOT
   claim it would answer YES; a HUMAN_APPROVES case should.

## What a pass looks like

- The subagent's captured output matches the template's actual
  `next_steps_hint`, `checklist`, and `human_questions` verbatim (proves the
  gate prints the real, current contract, not stale/cached text).
- The subagent's answers were genuinely derived from the printed text, not
  guessed (its own stated reasoning should reference the actual options shown).
- The final database state (`get_guidance_block_reason`, `task_transitions`,
  `transition_decisions`) matches what the subagent reported doing — no silent
  divergence between what it said happened and what was actually persisted.

## Known limitation

A cheap model asked to "answer honestly" can still rationalize a lazy
default and call it honest. Treat a suspiciously fast or generic-sounding
answer as a signal to re-run with a more detailed report requirement, not as
proof the gate is unfollowable.

## Improvement ideas (not yet implemented)

- Run the same fixed assignment across several cheap models (a
  low-tier Claude, a low-tier agy model, a low-tier GPT) and diff their behavior — a wording that
  only one model handles correctly is a wording problem, not a model problem.
- Automate the comparison step (subagent report vs. registry contract vs. DB
  state) into a script instead of manual reading, so this can run as an actual
  CI-style regression rather than an ad hoc one-off.
- Extend to a full multi-edge chain (INTAKE through DONE) in one subagent
  session, to catch guidance that's individually followable but confusing in
  sequence.
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