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 liqiongyu/lenny_skills_plus --skill running-offsitesgit clone --depth 1 https://github.com/liqiongyu/lenny_skills_plusWrote 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/liqiongyu/lenny_skills_plus/running-offsites)<a href="https://agentmods.dev/skills/liqiongyu/lenny_skills_plus/running-offsites"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/running-offsites/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/liqiongyu/lenny_skills_plus/running-offsites"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/running-offsites.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 | $0.00029 | $0.02336 |
| Opus 5.5 | $0.00012 | $0.00934 |
| Sonnet 5.5 | $0.00006 | $0.00467 |
| Haiku 4.5 | $0.00003 | $0.00234 |
Grade A, and why
running-offsites 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 2mo 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running Offsites
Scope
Covers
- Designing an offsite that produces durable alignment + decisions + momentum (not “good vibes”)
- Choosing the right format: 1-day whiteboard sprint, multi-day retreat, or remote-first quarterly bursts
- Creating conditions for deep work: laptops down, physical collaboration, and “out of day-to-day” space
- Building human connection before hard strategy work (so the room can disagree productively)
- Ending with clear artifacts: decisions, action plan, and follow-up communication that prevents backsliding
When to use
- “Plan a team offsite / retreat with a concrete agenda and outputs.”
- “Design a strategy offsite that results in decisions and owners.”
- “We’re remote-first—create a quarterly in-person ‘burst’ plan.”
- “Create the offsite prework + facilitation guide + logistics checklist.”
- “Turn our offsite into a documented plan and follow-up comms.”
When NOT to use
- You’re trying to fix deep interpersonal conflict with a workshop (“storytelling” won’t fix trust); do conflict repair first (or involve HR/leadership).
- You don’t know what you’re trying to achieve (use problem definition or product vision first).
- You need a single meeting agenda and facilitation plan, not a multi-session program (use
running-effective-meetings). - You need to design recurring team ceremonies or rituals (use
team-rituals; offsites are one-time or quarterly events, not ongoing cadences). - You need stakeholder buy-in for a specific proposal (use
stakeholder-alignment; an offsite may include alignment sessions, but the alignment campaign is a separate skill). - You need to build a presentation or keynote for one session (use
giving-presentations; this skill designs the full offsite program). - You need a large-scale event with complex vendor/contracting needs (use professional event planning support; this skill focuses on team-level offsites).
- The request is HR/legal/compliance-sensitive (escalate to humans and follow company policy).
What ships with it
13 files 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.
- eval/eval_config.json 659 B
- eval/SHOWCASE.md 5.0 KB
- eval/with_skill.md 40 KB
- eval/without_skill.md 22 KB
- README.md 1.4 KB
- references/CHECKLISTS.md 2.0 KB
- references/EXAMPLES.md 1.8 KB
- references/INTAKE.md 2.3 KB
- references/RUBRIC.md 4.2 KB
- references/SOURCE_SUMMARY.md 2.1 KB
- references/TEMPLATES.md 5.1 KB
- references/WORKFLOW.md 3.5 KB
- skillpack.json 367 B
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.
- 2mo ago First seen · 140 lines · 29 tokens per session scan A dca67bf30bfd
running-offsites is a skill published in the GitHub repository liqiongyu/lenny_skills_plus (53 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 2,336 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 2026-09-03.
running-offsites compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| running-offsitesliqiongyu/lenny_skills_plus | Skill | 53 | 5mo ago | Apache-2.0 | A | 29 | Claude Code, Codex |
| happiness-skillkangarooking/cangjie-skill | Skill | 12k | 1mo ago | MIT | A | 136 | Claude Code, Codex |
| setup-matt-pocock-skillsdevcxl/mattpocock-skills-zh | Skill | 530 | 3d ago | MIT | A | 43 | Claude Code, Codex |
| pixel-art-studioAnastasiyaW/codex-claude-code-config | Skill | 214 | yesterday | MIT | A | 349 | Claude Code |
| config-validatorjmagly/aiwg | Skill | 229 | yesterday | MIT | A | 15 | Claude Code, Codex |
| aiwg-regenerate-copilotjmagly/aiwg | Skill | 229 | yesterday | MIT | A | 25 | Claude Code, Codex |
| link-checkjmagly/aiwg | Skill | 229 | yesterday | MIT | A | 29 | Claude Code, Codex |