Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add richfrem/agent-plugins-skills --skill running-control-planegit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/richfrem/agent-plugins-skills/running-control-plane)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/running-control-plane"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/running-control-plane/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/running-control-plane"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/running-control-plane.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00202 | $0.01286 |
| Opus 5.5 | $0.00081 | $0.00514 |
| Sonnet 5.5 | $0.00040 | $0.00257 |
| Haiku 4.5 | $0.00020 | $0.00129 |
Grade A, and why
running-control-plane scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running the control plane
Gated engineering workflow: a task is registered in context/control_plane.db, specified, approved by a human signature, built in a worktree, verified and closed. Each mode below was a separate skill; its full workflow is a reference loaded when that mode starts.
Contents
Critical constraints
- Check the mode first. Run
python3 scripts/control_plane_mode.py status. When it saysdisabled, say so, skip registration and gating, and offer to enable. - Humans sign, agents never. The three gates (APPROVED, VERIFY_EXIT, DONE) need a human
ssh-keygen -Y sign. Never record a decision, approval or review skip on the human's behalf, and never run key enrollment. - Read before acting. Read the transition guidance and the database first; say which parts were read.
- One question per turn, answered from context and the running directives ledger first. Task artifacts live in
docs/plans/work-tasks/<task-id>/. - Stop on a blocked gate. State cause and cost; no workaround commands or direct database edits.
Quick start
python3 scripts/control_plane_mode.py status # is gating on?
python3 scripts/control_plane/coordinator.py transition-guidance --task-id <task-id>
Workflow
| Mode | Use when | Run | Workflow |
|---|---|---|---|
intake |
Starting any non-trivial task; resuming one | scripts/agent_control.py, scripts/control_plane/coordinator.py |
intake |
mode |
Enabling, disabling or checking gating | scripts/control_plane_mode.py enable | disable | status |
mode |
health |
Checking liveness, event bus, locks, memory, os metrics, "system monitor", or whether the signing identity is ready (status check) | scripts/kernel.py; signing check: setup_ciba_identity.py --check from setting-up-agentic-os |
health |
simulator |
Testing a transition, edge or its guidance without real state ("simulate", "dry run", "did I break the edge rules") | scripts/control_plane/run_transition_simulation.py |
simulator |
worktree |
Choosing or cleaning up a worktree for a task | scripts/capability_probe.py, scripts/worktree_manager.py |
worktree |
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 8.3 KB
- references/acceptance-criteria.md 4.0 KB
- references/agentic-os-skill-map.md 2.3 KB
- references/architecture/architecture.md 2.4 KB
- references/architecture/context-folder-patterns.md 3.3 KB
- references/architecture/vision.md 57 KB
- references/cheap-agent-transition-simulation.md 6.1 KB
- references/control-plane-architecture.md 9.0 KB
- references/control-plane-rebuild-recovery.md 6.2 KB
- references/control-plane-simulation-protocol.md 5.7 KB
- references/diagrams/agentic-os-memory-subsystem.mmd 1.4 KB
- references/diagrams/architecture-overview.mmd 3.1 KB
- references/diagrams/control-plane-architecture.mermaid 6.3 KB
- references/diagrams/control-plane-lifecycle-hardened-with-ciba-rar.mermaid 4.5 KB
- references/diagrams/control-plane-pipeline-happy-path.mermaid 5.0 KB
- references/diagrams/control-plane-pipeline.mermaid 9.3 KB
- references/diagrams/event-bus-architecture.mmd 2.4 KB
- references/diagrams/increment-b-human-only-transition-ssh-signing.mermaid 5.3 KB
- references/edge-matrix.md 13 KB
- references/fallback-tree.md 2.9 KB
- references/health-detailed-reference.md 7.1 KB
- references/healthy-transcript.md 3.8 KB
- references/implementation-ledger-contract.md 851 B
- references/intake-detailed-reference.md 3.1 KB
- references/modes/health.md 3.4 KB
- references/modes/intake.md 3.8 KB
- references/modes/mode.md 5.8 KB
- references/modes/simulator.md 6.2 KB
- references/modes/worktree.md 2.9 KB
- references/multi-round-external-review-protocol.md 2.6 KB
- references/worktree-reconciliation-and-multi-worktree-practices.md 5.8 KB
- requirements-dev.in 741 B
- requirements-dev.txt 603 B
- requirements.in 196 B
- requirements.txt 202 B
- scripts/agent_control.py 98 KB runs code
- scripts/audit_map_debt.py 6.1 KB runs code
- scripts/capability_probe.py 6.4 KB runs code
- scripts/check_plan_links.py 1.8 KB runs code
- scripts/control_plane_hooks.py 11 KB runs code
- scripts/control_plane_mode.py 12 KB runs code
- scripts/control_plane/__init__.py 842 B runs code
- scripts/control_plane/adapters.py 145 KB runs code
- scripts/control_plane/approver_policy.py 20 KB runs code
- scripts/control_plane/baseline_transition_report.py 4.0 KB runs code
- scripts/control_plane/constants.py 13 KB runs code
- scripts/control_plane/coordinator.py 57 KB runs code
- scripts/control_plane/edge_matrix.py 3.1 KB runs code
- scripts/control_plane/gate_evidence.py 9.9 KB runs code
- scripts/control_plane/gate1_approval.py 11 KB runs code
- scripts/control_plane/identity_layout.py 2.9 KB runs code
- scripts/control_plane/identity_setup.py 11 KB runs code
- scripts/control_plane/implementation_loop.py 11 KB runs code
- scripts/control_plane/implementation.py 3.7 KB runs code
- scripts/control_plane/inspection.py 3.9 KB runs code
- scripts/control_plane/installation_probe.py 5.7 KB runs code
- scripts/control_plane/isolation_check.py 14 KB runs code
- scripts/control_plane/measurement.py 39 KB runs code
- scripts/control_plane/pipeline_simulator.py 30 KB runs code
- scripts/control_plane/policy.py 32 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 71 lines · 202 tokens per session scan A 5faf181e77f4
running-control-plane is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 202 tokens to every session and 1,286 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-25.
Other skills, from other repositories
triage
Triage a GitHub repository's open issues by finding exact duplicates, rejecting evidenceably off-base requests, requesting concrete clarification, applying only existing labels, and opening a linked root-cause issue when multiple reports share one underlying invariant failure. Use when a maintainer asks to triage…
factory-handoff
Hand one exact agent-ready ticket to the central Factory runtime over the configured SSH forced-command boundary. Use when an operator asks to hand off an existing ticket or a prose request instead of implementing it in the current session.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
gitlab-portfolio
Use when you need a single-pane cross-repo health view across all vault-registered GitLab and GitHub projects. Discovers repos from overview.md frontmatter in /01-projects//, aggregates open issues, MRs, critical labels, and stale signals via parallel glab/gh calls, then writes an idempotent PORTFOLIO.md dashboard.…
reset-epic
Reset an epic's test data — close PRs, delete branches, reopen issues, revert code.
mindforge-remove-workspace
Remove a MindForge workspace and clean up worktrees.