Borrowing it
Nothing to install: this file belongs to st0012/cctop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/st0012/cctop/master/.agents/skills/cctop-restart/SKILL.mdgit clone --depth 1 https://github.com/st0012/cctopWrote 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.
[](https://agentmods.dev/skills/st0012/cctop/cctop-restart)<a href="https://agentmods.dev/skills/st0012/cctop/cctop-restart"><img src="https://agentmods.dev/badge/skills/st0012/cctop/cctop-restart/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.
<a href="https://agentmods.dev/skills/st0012/cctop/cctop-restart"><img src="https://agentmods.dev/badge/skills/st0012/cctop/cctop-restart.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.00357 |
| Opus 5 | $0.00029 | $0.00179 |
| Sonnet 5 | $0.00012 | $0.00071 |
| Haiku 4.5 | $0.00006 | $0.00036 |
Grade A, and why
cctop-restart 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 10d 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.
What it actually says
cctop Restart
When the user asks to restart or relaunch cctop during development, treat it as an end-to-end client refresh:
- Run
./script/build_and_run.sh --verifyfrom the repo root when available. - If the script is unavailable, run
make restart. - Verify
~/.cctop/bin/cctop-hookreports or contains the currentConfig.hookVersion. - Verify the running
CctopMenubarprocess path points at the current worktree/debug app.
Do not use make run or open ...CctopMenubar.app alone for restart requests; those can leave shims using a stale installed hook.
After cctop investigation, validation, delegated PR work, or any workflow that launches or kills the dev app, leave the verified debug app running for the developer unless the user explicitly asks to stop it or a concrete blocker prevents a safe relaunch. Report the running app path and installed hook version. Do not stop the app at the end merely to keep the process table tidy; the developer uses the app while reviewing the work.
For delegated task closeout after merge, make restart/app state part of the handoff: confirm the developer-facing app is running when relevant, then archive or park the driver thread. Only remove the driver worktree after confirming no app, build, test, or agent process is still running from it.
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.
- 10d ago First seen · 20 lines · 58 tokens per session scan A 8dfeecebe73c
cctop-restart is a skill published in the GitHub repository st0012/cctop (150 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 357 once invoked, about $0.0003 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.
Other skills, from other repositories
base
Universal coding patterns, constraints, TDD workflow, atomic todos.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
agf
Find local coding-agent sessions, inspect bounded metadata or summaries, and prepare a read-only resume plan with AGF. Use for finding prior work across agent CLIs, not for executing agents, deleting sessions, or reading full transcripts.
ad-creative-v2
Ad Creative workflow skill. Use this skill when the user needs Create, iterate, and scale paid ad creative for Google Ads, Meta, LinkedIn, TikTok, and similar platforms. Use when generating headlines, descriptions, primary text, or large sets of ad variations for testing and performance optimization and the operator…
armada-verification
Mandatory pre-completion verification and evidence checklist before reporting done.
pdlc-feature
An automated workflow for taking a new software feature from a description or requirements document through requirements, design, testing, implementation, review, and release preparation. It keeps one feature ID across the documents and requires tests before implementation.