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 sanada123/openclaw-skills --skill team-leadgit clone --depth 1 https://github.com/sanada123/openclaw-skillsWrote 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/sanada123/openclaw-skills/team-lead)<a href="https://agentmods.dev/skills/sanada123/openclaw-skills/team-lead"><img src="https://agentmods.dev/badge/skills/sanada123/openclaw-skills/team-lead/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/sanada123/openclaw-skills/team-lead"><img src="https://agentmods.dev/badge/skills/sanada123/openclaw-skills/team-lead.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 | $0.00186 | $0.03799 |
| Opus 5 | $0.00093 | $0.01899 |
| Sonnet 5 | $0.00037 | $0.00760 |
| Haiku 4.5 | $0.00019 | $0.00380 |
Grade A, and why
team-lead 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 11d 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 — 465 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Lead
The engineering management playbook for people who'd rather write code.
You got promoted (or promoted yourself) because you're a great engineer. Nobody taught you how to manage humans. This skill fills that gap — practical frameworks that work in real engineering teams, from 2-person startups to 50-person departments.
Core Philosophy
PEOPLE > PROCESS. A great team with bad process will fix the process. Bad team with great process will fail.
CLARITY > CONSENSUS. Decide, communicate, move. Don't committee-ize everything.
FEEDBACK > SILENCE. Uncomfortable truth now beats explosive problem later.
TRUST > CONTROL. Hire well, set expectations, then get out of the way.
GROW > RETAIN. People leave managers, not companies. Grow them or lose them.
When to Activate
- Running or joining a team as lead/manager
- Preparing for 1:1 meetings
- Hiring: writing job descriptions, interviewing, evaluating
- Giving difficult feedback
- Sprint planning, retros, standups
- Dealing with underperformers
- Remote team management
- First-time manager seeking guidance
- Performance review season
1. The 1:1 — Your Most Important Meeting
Structure (30 min, weekly, never cancel)
First 10 min: THEIR agenda
"What's on your mind?"
"What do you need from me?"
"Anything blocking you?"
Middle 10 min: YOUR agenda
Progress on goals
Feedback (both ways)
Career development check-in
Last 10 min: ACTION ITEMS
What will they do before next 1:1?
What will YOU do before next 1:1?
Write it down. Both of you.
Questions That Actually Work
| Purpose | Question |
|---|---|
| Open up | "What's the thing you're spending the most energy on right now?" |
| Unblock | "If you could change one thing about how we work, what would it be?" |
| Career | "What skill do you want to be known for in 2 years?" |
| Feedback | "What's one thing I could do differently to help you more?" |
| Satisfaction | "On a scale of 1-10, how happy are you at work? Why not higher?" |
| Trust | "Is there anything you're hesitant to tell me?" |
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.
- 11d ago First seen · 465 lines · 186 tokens per session scan A 4283de415be4
team-lead is a skill published in the GitHub repository sanada123/openclaw-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 186 tokens to every session and 3,799 once invoked, about $0.0009 per session on Opus 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 2026-08-31.
Other skills, from other repositories
cc-skill-project-guidelines-example
Project Guidelines Skill (Example).
grace-status
Show GRACE 4 project health across .grace context, graph, verification, active changes, scopes, and migration boundaries.
kanban-orchestrator
Kanban orchestrator: decompose, route, verify. No executing.
ergo-backlog-planning
Shape and execute multi-step work with the Ergo CLI, a repository-local backlog management tool. Use to plan software development, documentation, or general knowledge work as a series or graph of well-defined tasks. Use to define dependencies within that task backlog. Use to group tasks into epics when needed. Skip…
ralph-linear
Fetch Linear tickets and build them with ralph-starter.
ralph-task
Manage tasks across GitHub and Linear with ralph-starter.