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.
npx skills add jerpint/woltspace --skill holdgit clone --depth 1 https://github.com/jerpint/woltspaceWrote 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/jerpint/woltspace/hold)<a href="https://agentmods.dev/skills/jerpint/woltspace/hold"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/hold/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/jerpint/woltspace/hold"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/hold.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00042 | $0.00650 |
| Opus 5.5 | $0.00017 | $0.00260 |
| Sonnet 5.5 | $0.00008 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
hold 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 25d 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hold: keep a session up for a background task
The lodge rests a session once nobody has used it for the idle window the owner set (1 hour, 4 hours or 1 day). A rest stops the session's tmux and everything running inside it. The conversation is kept, and the next message wakes the session with its full history.
A rest normally costs you nothing. The exception is a task still running in the background: it dies with the session. A hold tells the lodge not to rest this session yet, because something is running in it.
When to hold
Hold only when a task must keep running while nobody talks to this session:
- a background job you started: a build, a dev server, a file watcher, a training run, a long test suite;
- one command you expect to run longer than the idle window.
Do not hold:
- to stay "available": a resting session wakes on the next message, with its conversation;
- while you are talking anyway: messages to you, typing in your terminal, and
your own
notify,woltspace session send,woltspace session spawnandpush-viewall count as use; - "just in case".
Usage
woltspace session hold 6h "npm run dev on :3000" # hold for 6 hours
woltspace session hold forever "tunnel for the demo" # until you release it
woltspace session hold off # release the hold
woltspace session hold # show this session's hold
- Durations:
90m,6h,2d, orforever. - The reason is required. Name the task that is running. The owner sees
every held session with its reason (in the lodge: Sessions, then Held; on
Telegram:
/holds) and can release it. The lodge log names it too.
Rules
- Release the hold (
hold off) as soon as the task ends. A forgotten hold keeps a session, with its memory and processes, up for nothing. Aforeverhold never ends on its own. - Prefer a duration to
forever, and pick the shortest one that covers the task. - A hold covers this session only. Run it from inside the session that
owns the task: it reads
$WOLTSPACE_WOLT_SESSION. Use--session <id>otherwise. - A hold also ends when the session stops for any other reason (it died, or someone stopped it), because the task it covered died with the session. If you restart the task, take a new hold.
- Holding a session that is not running fails.
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.
- 25d ago First seen · 63 lines · 42 tokens per session scan A a26f42d78d91
hold is a skill published in the GitHub repository jerpint/woltspace (22 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 650 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 2026-10-17.
hold compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| holdjerpint/woltspace | Skill | 22 | yesterday | MIT | A | 42 | Claude Code |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 316k | 7d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |