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-intakegit 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-intake)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/os-control-intake"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-control-intake/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-intake"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-control-intake.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 | $0.00094 | $0.00892 |
| Opus 5.5 | $0.00038 | $0.00357 |
| Sonnet 5.5 | $0.00019 | $0.00178 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
os-control-intake 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work Intake (os-control-intake)
Critical intake gateway for discovery, interview clarification, and four-pillar specification authoring before implementation.
Contents
Critical Constraints
- Confirm Approver Identity First: Real work lives in
context/control_plane.dbwhere only the human operator's signing key approves; simulation runs insimulation_control_plane.dbwith agent test identity (test-human@local). - Read Guidance & DB First: Read
transition_templates.yaml,transition-guidance, and SQLite DB first; say exactly which parts were read, never more. - Artifact Location & Running Ledger: Task artifacts live in
docs/plans/work-tasks/<task-id>/, never plans root. Maintain a running ledger of every human directive from first message. - Question Budget & Chat Answers: Answer from context first; ask only ONE question per turn. Never re-ask what is recorded and never dispute the human's account. Persist chat answers via
coordinate-transition --interactive(actor=human); never write interview answers as interviewer. - Pasteable Commands Only: Every command the human must run is complete and ready to paste, with no back-references, no vague references, and never "see above".
- Stop on Blocked Gate: On blocked gate, STOP and state cause and cost; no workaround commands (recovery approvals, direct DB edits). Never record a review skip on the human's behalf.
Quick start
Check advisory guidance for the active task state:
python3 scripts/control_plane/coordinator.py transition-guidance --task-id <task-id>
Workflow
- Read Guidance & State: Read
transition_templates.yamland SQLite DB enforcement before asking or acting. - Interview & Spec Synthesis: Interview for missing requirements. Compile the 4 pillars of
TASK_SPEC.md(The Job, The Why, Semantic Guardrails, Objective DoD). - Plan Drafting: Draft plan via native host facilities. For STANDARD work, evaluate execution topology (
select-loop-strategy) and conditionally invokegraph-plannerto compilegraph-manifest.jsonbefore review. - Stage Transitions: Transition through
INTAKE->INTERVIEW->DRAFT_PLAN->PLAN_REVIEWusingcoordinate-transition. - Advance to Approval: In
PLAN_REVIEW, once the plan is accepted, agent runscoordinate-transition --to AWAITING_APPROVAL.
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 823 B
- references/acceptance-criteria.md 60 B
- references/ciba-rar-transition-auth-flow.mermaid 66 B
- references/control-plane-architecture.mermaid 63 B
- references/control-plane-lifecycle-baseline-no-ciba-rar.mermaid 81 B
- references/control-plane-lifecycle-hardened-with-ciba-rar.mermaid 83 B
- references/control-plane-pipeline-happy-path.mermaid 70 B
- references/control-plane-pipeline.mermaid 59 B
- references/detailed-reference.md 59 B
- references/edge-matrix.md 34 B
- references/fallback-tree.md 54 B
- references/increment-b-human-only-transition-ssh-signing.mermaid 82 B
- references/multi-round-external-review-protocol.md 59 B
- references/os-control-intake-healthy-transcript.md 59 B
- scripts/agent_control.py 33 B runs code
- scripts/capability_probe.py 36 B runs code
- scripts/control_plane/__init__.py 45 B runs code
- scripts/control_plane/adapters.py 45 B runs code
- scripts/control_plane/approver_policy.py 52 B runs code
- scripts/control_plane/baseline_transition_report.py 63 B runs code
- scripts/control_plane/constants.py 46 B runs code
- scripts/control_plane/coordinator.py 48 B runs code
- scripts/control_plane/edge_matrix.py 48 B runs code
- scripts/control_plane/gate_evidence.py 50 B runs code
- scripts/control_plane/gate1_approval.py 51 B runs code
- scripts/control_plane/identity_layout.py 52 B runs code
- scripts/control_plane/identity_setup.py 51 B runs code
- scripts/control_plane/implementation_loop.py 56 B runs code
- scripts/control_plane/implementation.py 51 B runs code
- scripts/control_plane/inspection.py 47 B runs code
- scripts/control_plane/installation_probe.py 55 B runs code
- scripts/control_plane/isolation_check.py 52 B runs code
- scripts/control_plane/measurement.py 48 B runs code
- scripts/control_plane/pipeline_simulator.py 55 B runs code
- scripts/control_plane/policy.py 43 B runs code
- scripts/control_plane/ports.py 42 B runs code
- scripts/control_plane/proof_edges.py 48 B runs code
- scripts/control_plane/proof_policy.py 49 B runs code
- scripts/control_plane/receipt_provenance.py 55 B runs code
- scripts/control_plane/registry.py 45 B runs code
- scripts/control_plane/review_options.py 51 B runs code
- scripts/control_plane/review_selection.py 53 B runs code
- scripts/control_plane/run_transition_simulation.py 62 B runs code
- scripts/control_plane/signing_selftest.py 53 B runs code
- scripts/control_plane/simulation_identity.py 56 B runs code
- scripts/control_plane/snapshot.py 45 B runs code
- scripts/control_plane/ssh_signing.py 48 B runs code
- scripts/control_plane/state_machine.py 50 B runs code
- scripts/control_plane/transition_request.py 55 B runs code
- scripts/control_plane/transition_simulation_cases.py 64 B runs code
- scripts/control_plane/transition_templates.yaml 59 B
- scripts/control_plane/tty_signer.py 47 B runs code
- scripts/control_plane/wrappers/__init__.py 57 B runs code
- scripts/control_plane/wrappers/record_interview_question.py 74 B runs code
- scripts/control_plane/wrappers/record_retrospective.py 69 B runs code
- scripts/control_plane/wrappers/run_exit_verification.py 70 B runs code
- scripts/control_plane/wrappers/run_verify_exit_bundle.py 71 B runs code
- scripts/control_plane/wrappers/write_plan_document.py 68 B runs code
- scripts/interview_spec_engine.py 41 B runs code
- scripts/verify_gate_evidence.py 40 B 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.
- yesterday First seen · 67 lines · 94 tokens per session scan A 413bab2aab6a
os-control-intake is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed 2d ago), licensed MIT. It adds 94 tokens to every session and 892 once invoked, about $0.0004 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
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
ap-route-analyst
Inspect only enough read-only project information to recommend a route and list the facts behind that recommendation.
ap-roadmap-author
Write one dependency-ordered roadmap with owners, integration points, success items, and real checks.
ap-depth-prober
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
ap-fresh-verifier
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.