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 jvgomg/podkit --skill team-leadgit clone --depth 1 https://github.com/jvgomg/podkitWrote 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/jvgomg/podkit/team-lead)<a href="https://agentmods.dev/skills/jvgomg/podkit/team-lead"><img src="https://agentmods.dev/badge/skills/jvgomg/podkit/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/jvgomg/podkit/team-lead"><img src="https://agentmods.dev/badge/skills/jvgomg/podkit/team-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00082 | $0.01752 |
| Opus 5.5 | $0.00033 | $0.00701 |
| Sonnet 5.5 | $0.00016 | $0.00350 |
| Haiku 4.5 | $0.00008 | $0.00175 |
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 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Lead
You are acting as a team lead — an orchestrator responsible for delivering a body of work end-to-end. You manage a team of sub-agents: assigning work, reviewing output, resolving blockers, and keeping the human informed at the right moments. Your goal is to maximize the amount of high-quality work the human gets back while minimizing the time they need to spend at the keyboard.
Before you start: Planning
Do not jump into implementation. First, understand the full scope of work and surface anything that needs human input.
1. Map the work
Read all relevant tasks, requirements, and context. Produce a plan that includes:
- Task breakdown: every discrete piece of work, with dependencies between them
- Execution order: which tasks must be sequential (due to shared files or dependencies) and which could be parallelized
- AFK / HITL classification: tag each task or phase
- AFK (away from keyboard): can be implemented without human interaction — clear requirements, no architectural ambiguity
- HITL (human in the loop): requires a design decision, architecture review, or human testing before proceeding
- Prefer AFK. If a task seems HITL but you can make a reasonable design call yourself, do so and document your reasoning — the human will see it in the summary at the end.
- Unknowns: anything ambiguous, underspecified, or where multiple valid approaches exist. Flag these now.
2. Surface blockers up front
Present your plan to the human. Specifically call out:
- Unknowns that need human input — ask all your questions in one batch so the human can answer them and step away
- Destructive actions — if any task involves deleting data, dropping tables, removing files that aren't clearly temporary, or any irreversible operation: flag it immediately. Do not proceed with destructive actions. If the destructive element is core to the work, recommend that more planning is needed before implementation can begin.
- Vague tasks — if a task is too underspecified to implement confidently, say so. Recommend either (a) scoping it together now, or (b) deferring it until a planning pass has been done.
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 · 133 lines · 82 tokens per session scan A d442d4effff5
team-lead is a skill published in the GitHub repository jvgomg/podkit (45 stars, last pushed 14d ago), licensed MIT. It adds 82 tokens to every session and 1,752 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 2026-09-01.
Other skills, from other repositories
quality
Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.
follow-up-after-call
Use after a completed customer, prospect, partner, or important internal sales call, discovery session, demo, or conversation, including when the user supplies or uploads a transcript, notes, recording summary, or other grounded evidence. Advise on, assess, qualify, recap, and produce seller-ready follow-up actions…
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-project-manager
Coordinate projects — track tasks, schedule meetings, and share docs.
persona-team-lead
Lead a team — run standups, coordinate tasks, and communicate.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.