os-control-intake

os-control-intake is a skill for Claude Code from richfrem/agent-plugins-skills. It costs 94 tokens per session (892 once invoked), scanned A, original, MIT.

A guided starting point for substantial engineering work. It gathers the task details, asks focused questions, and records an agreed plan before coding begins.

In plain words
What is it for?
Use it before features, refactors, multi-file bug fixes, exploratory work, or new ideas that need clarification and a written work plan.
Why use it?
It reduces confusion caused by unclear requests, missing requirements, or plans made before understanding the project. It also keeps human instructions and approvals recorded.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the agent-agentic-os plugin — 14 skills, 2 agents, 3 hooks shipped together

Good fit Use it before features, refactors, multi-file bug fixes, exploratory work, or new ideas that need clarification and a written work plan.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/richfrem/agent-plugins-skills/os-control-intake
Install

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.

Any agent
npx skills add richfrem/agent-plugins-skills --skill os-control-intake
Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

Made for: Claude Code.

Or install agent-agentic-os, the plugin that ships this one along with the rest of its 14 skills, 2 agents, 3 hooks.

Wrote 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.

agentmods badge for os-control-intake

README.md
[![agentmods](https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-control-intake/github.svg)](https://agentmods.dev/skills/richfrem/agent-plugins-skills/os-control-intake)
Your own site
<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.

agentmods 80×15 button for os-control-intake

Your own site · 80×15
<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>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 892 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured yesterday against content hash 413bab2aab6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 45 executable files (scripts/agent_control.py, scripts/capability_probe.py, scripts/control_plane/__init__.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/agent-agentic-os/skills/os-control-intake/SKILL.md · 67 lines

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

  1. Confirm Approver Identity First: Real work lives in context/control_plane.db where only the human operator's signing key approves; simulation runs in simulation_control_plane.db with agent test identity (test-human@local).
  2. Read Guidance & DB First: Read transition_templates.yaml, transition-guidance, and SQLite DB first; say exactly which parts were read, never more.
  3. 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.
  4. 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.
  5. 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".
  6. 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

  1. Read Guidance & State: Read transition_templates.yaml and SQLite DB enforcement before asking or acting.
  2. Interview & Spec Synthesis: Interview for missing requirements. Compile the 4 pillars of TASK_SPEC.md (The Job, The Why, Semantic Guardrails, Objective DoD).
  3. Plan Drafting: Draft plan via native host facilities. For STANDARD work, evaluate execution topology (select-loop-strategy) and conditionally invoke graph-planner to compile graph-manifest.json before review.
  4. Stage Transitions: Transition through INTAKE -> INTERVIEW -> DRAFT_PLAN -> PLAN_REVIEW using coordinate-transition.
  5. Advance to Approval: In PLAN_REVIEW, once the plan is accepted, agent runs coordinate-transition --to AWAITING_APPROVAL.

Read the full file on GitHub · 67 lines

Files

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.

Changes

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.

  1. yesterday First seen · 67 lines · 94 tokens per session scan A 413bab2aab6a

Subscribe to this mod's changes

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.