disconnect

disconnect is a skill for Claude Code, Codex from PerpetualSoftware/pad. It costs 18 tokens per session (367 once invoked), scanned A, original, Apache-2.0.

A session command for stopping Pad push notifications, where Pad is the workspace tool used by the related skills. The disconnect applies to the current session.

In plain words
What is it for?
Use it to turn off Pad pushes for the current session, including when you are working outside the linked workspace.
Why use it?
It prevents this session from receiving further Pad updates when you no longer want them.

Skill for Claude CodeCodex

Part of the pad plugin — 6 skills shipped together

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 skills/perpetualsoftware/pad/disconnect
Any agent
npx skills add PerpetualSoftware/pad --skill disconnect
Clone the repo
git clone --depth 1 https://github.com/PerpetualSoftware/pad

Made for: Claude Code, Codex.

Or install pad, the plugin that ships this one along with the rest of its 6 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 disconnect

README.md
[![agentmods](https://agentmods.dev/badge/skills/perpetualsoftware/pad/disconnect.svg)](https://agentmods.dev/skills/perpetualsoftware/pad/disconnect)
Your own site
<a href="https://agentmods.dev/skills/perpetualsoftware/pad/disconnect"><img src="https://agentmods.dev/badge/skills/perpetualsoftware/pad/disconnect.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 367 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 $0.00018 $0.00367
Opus 5 $0.00009 $0.00183
Sonnet 5 $0.00004 $0.00073
Haiku 4.5 $0.00002 $0.00037

Measured 3d ago against content hash c460d0e43179, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

disconnect 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 3d 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/disconnect/SKILL.md · 31 lines

What it actually says

/pad:disconnect withdraws THIS session's consent to receive pad push notifications. It holds for the rest of the session even if the repo opted in via .pad.toml push.auto_arm — a disconnect must not be a lie.

If the pad CLI is missing (command not found), say so and point at https://getpad.dev/install. Otherwise ALWAYS run the disarm — do NOT gate it on finding a .pad.toml. Consent is scoped to this SESSION (keyed by the session, not the workspace), so a session that connected in one repo must be able to disconnect from anywhere, including a directory with no linked workspace; refusing to disarm there would leave it receiving pushes.

Steps:

  1. Run pad session disarm. This writes a session-scoped explicit-off marker (it does not delete config), so the session stops accepting pushes now and stays that way for its remaining life. It works regardless of the current directory's workspace.

  2. Tell the user they're disconnected. If the command reported that the repo has auto_arm on, add the honest caveat: this session is disconnected, but a NEW session in this repo will connect again — to turn that off permanently, remove push.auto_arm from .pad.toml (the same deliberate edit that turned it on).

Note: the monitor re-checks consent every couple of seconds and drops the open stream when it sees the disarm, so delivery stops within a brief window rather than lingering. Run /pad:status to confirm the state.

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. 3d ago First seen · 31 lines · 18 tokens per session scan A c460d0e43179

Subscribe to this mod's changes

disconnect is a skill published in the GitHub repository PerpetualSoftware/pad (146 stars, last pushed 3d ago), licensed Apache-2.0. It adds 18 tokens to every session and 367 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 2026-08-30.

Related

Other skills, from other repositories

docmancer

Work from the same local memory as every other coding agent on this machine. Recall prior decisions, preferences, instructions, and project conventions that Claude Code, Codex, Cursor, and other agents wrote here, with cited sources, fully local. Also searches a separate local technical-documentation index.

docmancer/docmancer · 62 tokens

Sverklo Code Intelligence

Gives you deep codebase understanding — semantic search, blast-radius analysis, PR review, and health audits.

sverklo/sverklo · 27 tokens

lians

Use Lians financial-grade agent memory - store and recall facts with a bitemporal model so stale revisions never contaminate context. Use whenever an agent needs persistent memory in finance, healthcare, or legal work, or when a task asks "what did we know on/before ", needs an audit trail, or must erase a data…

Lians-ai/Lians · 73 tokens

lians-integrate

Wire Lians memory into an existing agent codebase, test-first and minimal-diff. Use when the user asks to add persistent/compliance memory to their agent, integrate Lians, or replace a vector store with bitemporal memory.

Lians-ai/Lians · 53 tokens

memoryguard

Local-first MCP memory backend and governance console for coding agents. Auto-organize, quarantine, supersede, and rollback shared memories across multiple agents.

irisxc4/memoryguard · 32 tokens

engram

Local-first personal AI identity and memory layer for MCP-compatible coding tools (Claude Code, Codex, Cursor, and others). Use this skill when the user wants to continue from a previous session ("continue from last session", "pick up where we left off"), recall a past decision ("what did we decide", "what was our…

Patdolitse/piia-engram · 175 tokens