AccordAgents-desktop-app: Skill for Claude Code

.claude/skills/restart-the-app/SKILL.md

restart-the-app is a skill for Claude Code from juliakrivchikova/AccordAgents-desktop-app. It costs 57 tokens per session (732 once invoked), scanned A, original, Apache-2.0.

A safe restart procedure for the AccordAgents desktop app after changing its main process. It delays the restart so the current reply can be delivered first.

In plain words
What is it for?
Use it after changing src/main, when asked to restart the app, or before checking a change through the live Electron app.
Why use it?
It prevents a desktop app restart from cutting off the current conversation and checks that the temporary restart job is removed afterward.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; positional $N argument.

This is juliakrivchikova/AccordAgents-desktop-app's own configuration. It tells Claude Code how to work on AccordAgents-desktop-app itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AccordAgents-desktop-app configures →

Reuse

Borrowing it

Nothing to install: this file belongs to juliakrivchikova/AccordAgents-desktop-app. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/juliakrivchikova/AccordAgents-desktop-app/main/.claude/skills/restart-the-app/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/juliakrivchikova/AccordAgents-desktop-app

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 restart-the-app

README.md
[![agentmods](https://agentmods.dev/badge/skills/juliakrivchikova/accordagents-desktop-app/restart-the-app/github.svg)](https://agentmods.dev/skills/juliakrivchikova/accordagents-desktop-app/restart-the-app)
Your own site
<a href="https://agentmods.dev/skills/juliakrivchikova/accordagents-desktop-app/restart-the-app"><img src="https://agentmods.dev/badge/skills/juliakrivchikova/accordagents-desktop-app/restart-the-app/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 restart-the-app

Your own site · 80×15
<a href="https://agentmods.dev/skills/juliakrivchikova/accordagents-desktop-app/restart-the-app"><img src="https://agentmods.dev/badge/skills/juliakrivchikova/accordagents-desktop-app/restart-the-app.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 732 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 $0.00057 $0.00732
Opus 5.5 $0.00023 $0.00293
Sonnet 5.5 $0.00011 $0.00146
Haiku 4.5 $0.00006 $0.00073

Measured 1mo ago against content hash c6d10d3ce8c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

restart-the-app 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/restart-app-launchd.sh, scripts/restart-app.sh), 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.

.claude/skills/restart-the-app/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Restart AccordAgents safely

The app being restarted may host the current conversation. Schedule exactly one delayed restart, let the current reply reach the user, and ensure the new Electron process is detached from the agent session.

Restart

Run from the repository root:

/bin/bash .claude/skills/restart-the-app/scripts/restart-app.sh

Then send the reply. The helper waits 25 seconds before replacing Electron, so the reply can reach the user first.

The scheduler builds first and clears the marker if submission fails. The pending marker is a safety latch: one submission can perform at most one restart. The helper consumes it before touching Electron and removes its own launchd job on every exit path. If launchd ever retries the helper, the retry must skip the restart because the marker is gone.

Verify on the next turn

First prove the transient job is gone. A still-loaded job is a failure because launchctl submit creates an inferred KeepAlive job on this machine:

TASK_UID=$(id -u)
if launchctl print "gui/$TASK_UID/com.accordagents.restart" >/dev/null 2>&1; then
  echo "ERROR: restart job is still loaded"
  launchctl remove com.accordagents.restart
  exit 1
fi

Then prove that exactly one current Electron main process exists, started after the request and detached from the agent process tree:

REPO=$(git rev-parse --show-toplevel)
APP_BIN="$REPO/node_modules/electron/dist/Electron.app/Contents/MacOS/Electron"
APP_PIDS=$(ps -axo pid=,command= | awk -v bin="$APP_BIN" '$2 == bin { print $1 }')
set -- $APP_PIDS
if [ "$#" -ne 1 ]; then
  echo "ERROR: expected one Electron process, found $#"
  exit 1
fi
ps -o pid=,ppid=,lstart=,command= -p "$1"

There must be exactly one match and its PPID must be 1. Confirm the real renderer through the repo's electron-desktop-qa workflow before calling a main-process change verified.

Failure handling

  • If the job remains loaded, remove it immediately and do not resubmit it until the cleanup failure is understood.
  • If the app did not return, inspect .scratch/app.log; do not claim success or start a second instance against the same user-data directory.
  • Never use a broad pkill Electron. The helper matches only this repository's Electron binary.
  • Never restart before a successful build.

Read the full file on GitHub · 87 lines

Files

What ships with it

2 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. 1mo ago First seen · 87 lines · 57 tokens per session scan A c6d10d3ce8c7

Subscribe to this mod's changes

restart-the-app is a skill published in the GitHub repository juliakrivchikova/AccordAgents-desktop-app (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 732 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 2026-09-21.

Related

Other skills, from other repositories

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.

paperclipai/paperclip · 30 tokens

Cortex

LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…

danielmiessler/LifeOS · 184 tokens

rowboat-spaces

How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.

rowboatlabs/rowboat · 60 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens