wolfpack-tailnet-control

wolfpack-tailnet-control is a skill for Claude Code, Codex from almogdepaz/wolfpack. It costs 31 tokens per session (1,824 once invoked), scanned A, original, MIT.

A command-line tool for managing Wolfpack sessions, which are local or Tailscale-connected coding-agent workspaces. It can create top-level sessions, start child agents, and inspect or control existing sessions.

In plain words
What is it for?
Use it to start a project session with a selected coding harness, split work among child agents, provide plans and prompts, and inspect or control sessions.
Why use it?
It removes the need to manage agent sessions through undocumented browser or private HTTP interfaces. The canonical CLI keeps session creation and agent spawning in one documented workflow.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Codex.

Good fit Use it to start a project session with a selected coding harness, split work among child agents, provide plans and prompts, and inspect or control sessions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/almogdepaz/wolfpack/wolfpack-tailnet-control
Install

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.

Any agent
npx skills add almogdepaz/wolfpack --skill wolfpack-tailnet-control
Clone the repo
git clone --depth 1 https://github.com/almogdepaz/wolfpack

Made for: Claude Code, Codex.

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 wolfpack-tailnet-control

README.md
[![agentmods](https://agentmods.dev/badge/skills/almogdepaz/wolfpack/wolfpack-tailnet-control/github.svg)](https://agentmods.dev/skills/almogdepaz/wolfpack/wolfpack-tailnet-control)
Your own site
<a href="https://agentmods.dev/skills/almogdepaz/wolfpack/wolfpack-tailnet-control"><img src="https://agentmods.dev/badge/skills/almogdepaz/wolfpack/wolfpack-tailnet-control/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 wolfpack-tailnet-control

Your own site · 80×15
<a href="https://agentmods.dev/skills/almogdepaz/wolfpack/wolfpack-tailnet-control"><img src="https://agentmods.dev/badge/skills/almogdepaz/wolfpack/wolfpack-tailnet-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,824 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00031 $0.01824
Opus 5.5 $0.00012 $0.00730
Sonnet 5.5 $0.00006 $0.00365
Haiku 4.5 $0.00003 $0.00182

Measured 21d ago against content hash f75b56b3a685, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wolfpack-tailnet-control 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 21d 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.

skills/wolfpack-tailnet-control/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wolfpack Session Control

Use the canonical CLI. Do not discover or reconstruct browser/private HTTP flows. Wolfpack uses its ordinary global API auth policy and adds no inter-session authorization layer.

Fast path

A top-level project session:

wolfpack session create <project> --harness <pi|claude|codex|gemini|cursor> --prompt '<instruction>' --json

A child of the current agent (same harness by default; full-startup assignment):

# Pi child: resolve the role model explicitly; use the reviewer setting for review.
IMPLEMENTER_MODEL="${WOLFPACK_IMPLEMENTER_MODEL:-openai-codex/gpt-6.1-sol:high}"
REVIEWER_MODEL="${WOLFPACK_REVIEWER_MODEL:-openai-codex/gpt-6.1-sol:high}"
wolfpack agent spawn <project> --harness pi --name 200-implementation --model "$IMPLEMENTER_MODEL" --plan .plans/000-task.md --notify-parent --json
# --model requires a pi child, not a pi parent. Omit it for other child harnesses.
wolfpack agent spawn <project> --harness claude --name 200-review --plan .plans/000-task.md --notify-parent --json

wolfpack session open is only a deprecated child-spawn alias. Never use it for a top-level request. Replace <project> with --project-dir <path> when the user selects an existing directory outside the configured projects root; never pass both selectors. The CLI resolves relative paths and the server validates/canonicalizes the directory. Both creation commands perform one server-owned request and pass startup instructions without inheriting parent transcript/context. --harness <pi|claude|codex|gemini|cursor> overrides the inherited child harness while preserving parent lineage; shell is not a child harness. --model is child-only and requires a Pi child; an explicit user/project model overrides the role environment/default.

Use --name <session> for child agents and choose a short meaningful issue/role slug, for example 200-implementation, 200-delivery-review, or auth-boundary-audit. Avoid generic *-sub-agent names when the task purpose is known; Wolfpack will allocate a numbered suffix if the requested name is already taken. Prefer --plan <file> for plan work: Wolfpack generates the compact handoff prompt and verifies the file exists without copying plan contents into the parent transcript. Use --prompt-file <file> for long bespoke instructions. Use raw --prompt only for one short prompt sentence. Do NOT paste repository policy, architecture context, or full plans into the launch command.

Read the full file on GitHub · 83 lines

Files

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.

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. 21d ago Changed · +2 lines f75b56b3a685
  2. 22d ago Changed · +1 lines b21590f93430
  3. 25d ago Changed 4ce28482239a
  4. 1mo ago Changed · +3 lines bbef7f87e26e
  5. 2mo ago Changed · +5 lines e07e7d444fc9
  6. 2mo ago Changed · +11 lines 6a8aa8c2fdfd
  7. 2mo ago First seen · 61 lines · 31 tokens per session scan A d876a5c4176b

Subscribe to this mod's changes

wolfpack-tailnet-control is a skill published in the GitHub repository almogdepaz/wolfpack (50 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 1,824 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 2026-08-30.

Related

wolfpack-tailnet-control compared with skills from other repositories

wolfpack-tailnet-control next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
wolfpack-tailnet-controlalmogdepaz/wolfpackSkill50todayMITA31Claude Code, Codex
experiment-tracking-swanlabOrchestra-Research/AI-Research-SKILLsSkill14k1mo agoMITA40Claude Code, Codex
debugging-executionsn8n-io/n8nSkill210ktodaynoneA86Claude Code, Codex
suggest-automationsn8n-io/n8nSkill210ktodaynoneA87Claude Code, Codex
standardize-health-datathetahealth/mirobodySkill1.4ktodayApache-2.0A133Claude Code
pandic-officeTeam-Commonly/commonlySkill1.4ktodayApache-2.0A59Claude Code, Codex
apify-skillzeenie-ai/OpenCompanySkill1.1ktodayMITA48Claude Code