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 wolfgit 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/wolf)<a href="https://agentmods.dev/skills/jerpint/woltspace/wolf"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/wolf/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/wolf"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/wolf.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 | $0.00036 | $0.01670 |
| Opus 5.5 | $0.00014 | $0.00668 |
| Sonnet 5.5 | $0.00007 | $0.00334 |
| Haiku 4.5 | $0.00004 | $0.00167 |
Grade A, and why
wolf 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 14d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wolf — Cron Scheduler
The wolf is the lodge's scheduler. Each wolt owns its crons in its own
wolt/wolf.json; the wolf scans every wolt every 30 seconds, and when a cron is
due it starts a session for the owning wolt with the cron's message as the
prompt, then sends a 🐺 notification.
Manage crons with woltspace wolf. It talks to the lodge, which validates
everything before writing wolf.json, so a mistake comes back as an error
instead of a cron that silently never fires.
Time zone
The wolf fires in the lodge machine's local time. 0 9 * * * means 09:00 on
the clock of the machine the lodge runs on — no UTC conversion. woltspace wolf list prints the zone it is using, and every time it shows is in that zone.
A container lodge runs on UTC unless its env file sets TZ; to choose the
zone and move existing crons safely, see
Time zone.
Add
The message (what the session is told to do) is read from stdin. Use a single-quoted heredoc so the shell leaves it alone:
woltspace wolf add --cron '0 9 * * 1-5' --notify telegram <<'WOLF_MSG'
Write today's standup notes from yesterday's commits.
WOLF_MSG
One-off, fires once at a lodge-local time and then removes itself:
woltspace wolf add --at 2026-03-22T14:30 <<'WOLF_MSG'
Check whether the deploy went through and tell jerpint.
WOLF_MSG
--woltdefaults to you ($WOLTSPACE_WOLT_NAME); pass it to schedule for another wolt.--namedefaults to the message's first few words (write-today-s-standup), made unique in that wolt.--notify telegram|slackalso pings your human there when it runs ("🐺 woke up: " + session link). Leave it out and the wolf is quiet; the run still shows inwoltspace wolf runsand on the lodge's wolves page. Slack needsSLACK_NOTIFY_CHANNELset.--message TEXTinstead of stdin for a one-liner.--dry-runshows the entry and the resulting file, writes nothing.--jsonon any command for machine-readable output.
What ships with it
1 file 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.
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.
- 14d ago Changed · +3 lines 705f3e34598a
- 15d ago Changed 2537a04f11da
- 1mo ago Changed · +31 lines 9200f41bf1e3
- 2mo ago First seen · 102 lines · 36 tokens per session scan A 5ca5ffc0f4eb
wolf is a skill published in the GitHub repository jerpint/woltspace (22 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 1,670 once invoked, about $0.0001 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 2026-09-09.
wolf compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wolfjerpint/woltspace | Skill | 22 | today | MIT | A | 36 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 3d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 6d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |