control

control is a command for Claude Code from Generous-Corp/pulp. It costs 15 tokens per session (314 once invoked), scanned A, original, MIT.

A safety-focused interface for discovering installed Pulp runtime instances and calling their registered, typed operations through the Pulp command-line tool.

In plain words
What is it for?
Use it to list profiles and instances, inspect status, request permission for a typed operation, make a bounded call, watch permitted operations, and audit saved evidence.
Why use it?
It discourages guessing instance details or using unapproved fallbacks, and keeps operation grants, requests, and returned evidence tied to the exact runtime instance.

Command for Claude Code

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.

agentmods
npx agentmods add commands/generous-corp/pulp/control
Clone the repo
git clone --depth 1 https://github.com/Generous-Corp/pulp

Made for: Claude Code.

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 control

README.md
[![agentmods](https://agentmods.dev/badge/commands/generous-corp/pulp/control.svg)](https://agentmods.dev/commands/generous-corp/pulp/control)
Your own site
<a href="https://agentmods.dev/commands/generous-corp/pulp/control"><img src="https://agentmods.dev/badge/commands/generous-corp/pulp/control.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 314 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.00314
Opus 5 $0.00008 $0.00157
Sonnet 5 $0.00003 $0.00063
Haiku 4.5 $0.00002 $0.00031

Measured today against content hash ec6bab41e403, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

control 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 today.

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.

.claude/commands/control.md · 36 lines

What it actually says

Use the installed pulp command and the canonical broker. Start with read-only discovery; never guess an instance, choose "newest", or add a host/port/raw protocol fallback.

pulp control profiles --json
pulp control instances --json
pulp control status --instance "$INSTANCE_ID" --explain --json

For a typed operation, inspect the exact live instance and request only that operation. Do not substitute a design-time agent capability row for runtime authority.

pulp control grant-request --instance "$INSTANCE_ID" \
  --operation dev.pulp.gpu/health.read@1 --json
pulp control call --instance "$INSTANCE_ID" \
  dev.pulp.gpu/health.read@1 --params '{}' --json

Use watch only when the operation's registry contract permits it. Preserve the returned registration, publication, instance, grant, request, idempotency, and receipt identities in evidence. A GPU-health response is one bounded runtime snapshot; it is not by itself an A3 campaign or terminal disposition.

Ask before requesting broader reusable grants, invoking mutations, revoking a grant, or starting/stopping a trace. Use pulp control audit PATH --json for offline artifact audit. If the broker or typed operation is unavailable, report that state; do not recreate the retired Inspector transport.

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. today First seen · 36 lines · 15 tokens per session scan A ec6bab41e403

Subscribe to this mod's changes

control is a command published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 314 once invoked, about $0.0001 per session on Opus 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 2026-09-04.