set-gate

set-gate is a skill for Claude Code from tu11aa/squadrant. It costs 49 tokens per session (620 once invoked), scanned A, original, MIT.

A setting for choosing how a coding agent handles permission requests: use the add-on's classifier, leave decisions to the agent, or disable the add-on's gate. It can also show where the current setting came from.

In plain words
What is it for?
It helps read the current gate mode and set it to on, off, or auto without restarting the background process.
Why use it?
It gives you a way to control or inspect permission handling when testing unattended work or when the default classifier behaves incorrectly.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the squadrant plugin — 27 skills shipped together

Good fit It helps read the current gate mode and set it to on, off, or auto without restarting the background process.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tu11aa/squadrant/set-gate
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 tu11aa/squadrant --skill set-gate
Clone the repo
git clone --depth 1 https://github.com/tu11aa/squadrant

Made for: Claude Code.

Or install squadrant, the plugin that ships this one along with the rest of its 27 skills.

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 set-gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/tu11aa/squadrant/set-gate/github.svg)](https://agentmods.dev/skills/tu11aa/squadrant/set-gate)
Your own site
<a href="https://agentmods.dev/skills/tu11aa/squadrant/set-gate"><img src="https://agentmods.dev/badge/skills/tu11aa/squadrant/set-gate/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 set-gate

Your own site · 80×15
<a href="https://agentmods.dev/skills/tu11aa/squadrant/set-gate"><img src="https://agentmods.dev/badge/skills/tu11aa/squadrant/set-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 620 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 $0.00049 $0.00620
Opus 5.5 $0.00020 $0.00248
Sonnet 5.5 $0.00010 $0.00124
Haiku 4.5 $0.00005 $0.00062

Measured 1mo ago against content hash 82721bb11257, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

set-gate 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 1mo 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.

plugin/skills/set-gate/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.

squadrant:set-gate — Permission Gate Mode

defaults.gate.mode (#782/#828) controls whether squadrant's own classifier decides a router-backed crew/captain's PermissionRequest, instead of Claude Code's built-in auto-mode classifier (which is hardcoded to Claude Sonnet 5 and fails closed on a router backend).

Modes

Mode Meaning
on squadrant's gate decides — the configured engine (router or auto-gate) classifies each request.
off The gate never touches a PermissionRequest — the agent's normal permission flow is untouched.
auto Yield to the agent's own built-in classifier. Default when the field is absent — zero behavior change.

Get current mode

squadrant gate mode

Prints the effective mode and where it came from: env (the SQUADRANT_GATE override), config (defaults.gate.mode), or default (auto, field absent).

Set mode

squadrant gate mode on
squadrant gate mode off
squadrant gate mode auto
  • Validates the value (errors with the 3 valid options if invalid).
  • Writes defaults.gate.mode via the existing saveConfig atomic path.
  • Prints old → new.
  • No daemon bounce needed — defaults.gate.mode is not daemon-cached; the CLI reads it live on every hook invocation.
  • If SQUADRANT_GATE is set in the current shell session, it still overrides the config value for that session — the command warns when this is the case.

Status (classifier + credential, nice-to-have)

squadrant gate status

Prints the effective mode + source, the resolved engine, the resolved classifier model, and whether the engine's credential resolves (present/absent). Never prints the credential value itself.

Manual edit (fallback)

If the CLI is unavailable, edit ~/.config/squadrant/config.json directly:

{
  "defaults": {
    "gate": {
      "mode": "on"
    }
  }
}

Valid values: "on" | "off" | "auto". Absent field is equivalent to "auto".

Read the full file on GitHub · 67 lines

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. 1mo ago First seen · 67 lines · 49 tokens per session scan A 82721bb11257

Subscribe to this mod's changes

set-gate is a skill published in the GitHub repository tu11aa/squadrant (2 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 620 once invoked, about $0.0002 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 2026-09-26.

Related

set-gate compared with skills from other repositories

set-gate next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
set-gatetu11aa/squadrantSkill2yesterdayMITA49Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code