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 os-control-modegit 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/os-control-mode)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/os-control-mode"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-control-mode/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/os-control-mode"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-control-mode.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 | $0.00152 | $0.00731 |
| Opus 5.5 | $0.00061 | $0.00292 |
| Sonnet 5.5 | $0.00030 | $0.00146 |
| Haiku 4.5 | $0.00015 | $0.00073 |
Grade A, and why
os-control-mode 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 yesterday.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Control Plane Mode (os-control-mode)
The control plane is more than one switch: the os-control-intake family of skills, a rule, two git guards in .git/hooks, and a declared mode. This skill flips them together and proves the result, so a repo is never left half on.
Contents
Critical Constraints
- Explicit Request Only: Only on explicit user request naming control plane or gating. Never autonomously.
- Never Bypass Blocked Guards: A blocked guard means stop, report why, and ask.
- Confirm Before Applying: Run
--dry-run, explain plan, and require explicit confirmation before--yes. - No Manual Hook Edits: Do not edit
AGENTS.md, hooks, or ownership files manually. Use the CLI script.
Quick start
Check current control plane mode and consistency:
python3 scripts/control_plane_mode.py status
Workflow
- Check Status: Inspect
statusoutput to see active mode and hook wiring. - Dry Run Plan: Execute
disable --dry-runorenable --dry-runto preview actions. - Execute Toggle: With user confirmation, apply with
--yes:python3 scripts/control_plane_mode.py disable --yes - Re-verify: Run
statusto confirm expected state.
What Each Mode Does
| Mode | Order | Rationale |
|---|---|---|
disable |
declare disabled -> unwire guards -> ownership -> sync |
gates go off first; machinery removed after |
enable |
ownership -> sync -> install/wire guards -> declare enabled |
gates only come on once machinery exists |
Verification
Confirm consistency and exit code (0 = consistent):
python3 scripts/control_plane_mode.py status --json
References
- acceptance-criteria.md — Acceptance criteria for control plane state toggles.
- fallback-tree.md — Recovery procedures when toggling or syncing fails.
- control-plane.manifest.json — Declared manifest of control plane members and git guards.
What ships with it
6 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.
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.
- yesterday First seen · 74 lines · 152 tokens per session scan A c3bac090c9d3
os-control-mode is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed 2d ago), licensed MIT. It adds 152 tokens to every session and 731 once invoked, about $0.0006 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 2026-10-16.
Other skills, from other repositories
release
Cut and publish a full stable NAC release after main, release-PR, and publication CI pass. Use when a maintainer asks for a stable version bump, tag, or GitHub Release. Never use for release candidates; NAC RC releases are automated.
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-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
release-revoke
Revoke or rollback a pi-agent-dashboard release: delete the GitHub Release, remove the git tag locally and on origin, deprecate the npm version (npm unpublish is blocked after 72h), and optionally revert the release commit. Use when the user says "revoke release", "rollback release", "delete release", "unpublish…
ap-work-group-manager
Divide one accepted work group only when at least two useful workers can have non-overlapping ownership.