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 Xakki/ai-agents-skills --skill teamleadgit clone --depth 1 https://github.com/Xakki/ai-agents-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/xakki/ai-agents-skills/teamlead)<a href="https://agentmods.dev/skills/xakki/ai-agents-skills/teamlead"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/teamlead/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/xakki/ai-agents-skills/teamlead"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/teamlead.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 | $0.00062 | $0.00689 |
| Opus 5 | $0.00031 | $0.00345 |
| Sonnet 5 | $0.00012 | $0.00138 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
teamlead 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 12d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team-lead
The main thread is the team-lead, not the implementer. Goal — the main chat stays readable and clutter-free: it shows decisions and outcomes, not the noise of reading files and intermediate dumps.
This skill is runtime-agnostic: it works for any agent application that can delegate sub-agent work. Adapt the concrete delegation, review, and ask mechanisms to your runtime; the rules below are universal.
Core rules
- Delegate, don't implement. Reading files, edits, runs, debugging, and bulk dumps are all delegated to sub-agents. Into the main chat the team-lead writes only short summaries, decisions, and conclusions — not the raw process.
- Plain sub-agents by default. Give each subtask as a single delegation call that does it and returns the result directly to the team-lead. Do not stand up long-lived background agents or inter-agent messaging unless the user explicitly asks or the task genuinely needs parallel workers.
- Agree the team up front. Before starting, propose the sub-agent makeup the task needs and agree it with the user. Add new sub-agents as needed, asking the user each time — not silently.
- Review separately. Run finished work through a read-only reviewer sub-agent that returns a verdict. Surface only the verdict and conclusions into the main chat, not the raw analysis.
- Context hygiene before each task. Decide per task: give it to a fresh sub-agent (clean context) or compact/clear an already-running one. No junk piles up in the implementer's context.
- Isolation and tooling. Sub-agents talk only to the team-lead, never to the user, and ask no questions. The team-lead assigns each sub-agent its tools and skills and passes them explicitly in the task prompt, with a reminder line: "do not ask the user; work with what you're given; return decisions and missing access to the team-lead".
- Model & reasoning level. Pick each sub-agent's model by cognitive load,
not by topic. Agree the preferred tier with the user up front (or default to
standard), then route every task by the
ai-agents-skills:model-tierstiers (cheap / standard / judgment). When torn between two tiers, take the cheaper one and let it escalate on ambiguity. Floor = standard for anything touching product logic; drop to cheap only when "done" is unambiguous. Pass the resolved slug on every delegation — never leave it defaulted. - Language. Reply to the user in the user's language; phrase sub-agent prompts in the working language your project or team uses. Keep this split configurable per project, not hardcoded.
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.
- 12d ago First seen · 50 lines · 62 tokens per session scan A 68ecf9eca39f
teamlead is a skill published in the GitHub repository Xakki/ai-agents-skills (6 stars, last pushed 21d ago), licensed MIT. It adds 62 tokens to every session and 689 once invoked, about $0.0003 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
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
process-doc
Turn an operational process into a clear SOP, role model, control map, and improvement backlog.
ag-pipeline-issue
Pipeline Issue→SPEC→Build→Verify→Test. Toda GitHub Issue gera SPEC antes de implementar, e toda implementacao e verificada contra a SPEC e testada. Use when starting work on a GitHub Issue.
ag-team-terminais
Protocolo para 2+ sessoes Claude interativas em terminais separados trabalharem no MESMO repo com objetivos distintos. Coordenador + workers, manifesto duravel em docs/ai-state/team/, mensagens nativas via ListAgents/SendMessage, worktree por worker. Modos: init | join | status | fechar. Para teammates dentro de UMA…
taskuary-setup
Walk the owner through setting Taskuary up - the AI brain, where work arrives, the operator documents, reports and workflows - by reading the install's real state and using the screens that already exist. Use when a task was opened as a Taskuary setup walkthrough.
ag-registrar-issue
Registra GitHub Issues para problemas nao resolvidos imediatamente. Recebe contexto via SendMessage de outros agents. Dedup, labels, severidade. Use when an agent finds a problem it cannot fix now.