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 digginggit 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/digging)<a href="https://agentmods.dev/skills/jerpint/woltspace/digging"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/digging/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/digging"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/digging.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 | $0.00067 | $0.00973 |
| Opus 5.5 | $0.00027 | $0.00389 |
| Sonnet 5.5 | $0.00013 | $0.00195 |
| Haiku 4.5 | $0.00007 | $0.00097 |
Grade A, and why
digging scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dig into an owned machine
Digging means temporarily using the owner's existing SSH access. The wolt stays resident in its home colony: connect, do the authorized work, leave a local handoff for future wolts on that machine, disconnect, and report home.
Prefer woltspace dig over invoking ssh directly whenever the digging command
is available. The wrapper makes the intended wolt and destination visible,
rechecks the resolved target, preserves the handoff convention, and records a
small non-secret audit trail. It does not create a security boundary against a
wolt running as the same Unix user.
Find or create the approval
Run woltspace dig list --json. Use an existing grant only when its wolt and
destination match the human's request.
If none matches and the named destination is an unambiguous existing SSH alias, set up the dig grant yourself rather than asking the human to remember CLI syntax. Choose a short lowercase grant name and run:
woltspace dig grant newbox newbox --wolt "$WOLTSPACE_WOLT_NAME"
Creating the grant only records a pointer to existing SSH access; it copies no key, certificate, agent credential, or token. If the destination, wolt, or intended work is ambiguous, ask before granting. Never guess a hostname or browse unrelated SSH destinations looking for somewhere to connect.
The grant records Woltspace consent; the SSH user's actual permissions remain the authority. Do not create accounts, keys, tunnels, or broader server access unless the human separately asks for that work.
Connect safely
Immediately before the first connection in a task, show the human the grant
name and resolved user@host:port, briefly state the intended work, and ask for
confirmation. A stored grant is not standing permission to connect.
Skip that confirmation only when the human's current instruction explicitly says that permission is not required, says to proceed without asking, or gives equally clear authorization to connect immediately. Do not infer a permanent waiver from an earlier task or from the mere existence of SSH access. Once the human confirms a task, do not repeatedly ask for every bounded command needed to complete that same task unless the target or scope 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.
- 1mo ago First seen · 98 lines · 67 tokens per session scan A 72e4d8fad6a2
digging is a skill published in the GitHub repository jerpint/woltspace (22 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 973 once invoked, about $0.0003 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.
digging compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| diggingjerpint/woltspace | Skill | 22 | yesterday | MIT | A | 67 | Claude Code |
| gke-compute-classesgoogle/skills | Skill | 24k | today | Apache-2.0 | A | 83 | Claude Code, Codex |
| gke-workload-securitygoogle/skills | Skill | 24k | today | Apache-2.0 | A | 171 | Claude Code, Codex |
| gke-reliabilitygoogle/skills | Skill | 24k | today | Apache-2.0 | A | 85 | Claude Code, Codex |
| cloud-architectJeffallan/claude-skills | Skill | 12k | 11d ago | MIT | A | 71 | Claude Code |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 3.9k | today | Apache-2.0 | A | 30 | Claude Code |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | today | MIT | A | 78 | Claude Code |