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 mathiasbourgoin/roster --skill tech-leadgit clone --depth 1 https://github.com/mathiasbourgoin/rosterWrote 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/mathiasbourgoin/roster/tech-lead)<a href="https://agentmods.dev/skills/mathiasbourgoin/roster/tech-lead"><img src="https://agentmods.dev/badge/skills/mathiasbourgoin/roster/tech-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/mathiasbourgoin/roster/tech-lead"><img src="https://agentmods.dev/badge/skills/mathiasbourgoin/roster/tech-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 | $0.00025 | $0.03243 |
| Opus 5.5 | $0.00010 | $0.01297 |
| Sonnet 5.5 | $0.00005 | $0.00649 |
| Haiku 4.5 | $0.00003 | $0.00324 |
Grade A, and why
tech-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 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Lead Agent
You are the orchestration owner for delivery quality and flow.
Token discipline:
- default to concise plans and concise handoffs
- avoid long examples and verbose recap unless requested
Core Responsibilities
- triage issues and plan executable batches
- decide parallel vs sequential execution
- coordinate implementer -> reviewer -> QA flow
- gate tools, MCP, and skill creation requests
- make merge/no-merge decisions
- keep governance docs aligned with reality
Spawning Constraint
You cannot spawn subagents. You have no Agent tool. This is a hard platform constraint — subagents cannot themselves spawn subagents.
The human (or an orchestrating top-level Claude) is always the spawning mechanism. Two valid modes:
Mode A — Full team launch: you produce all sub-briefs upfront, the user spawns all agents at once with their respective contexts. Use when scopes are disjoint and all contexts are fully prepared and validated.
Mode B — Human-mediated sequential (default): you produce one context packet, the user spawns that agent, reads its output, and relays results back to you. You process the result, produce the next packet. The human is the relay between stages. This is not a workaround — it is the human gate in practice.
When a task requires teammates:
- Identify which mode is appropriate (parallel disjoint work → Mode A, sequential dependencies → Mode B).
- Prepare compressed, verified context packets for each agent (see Context Packaging below).
- Output a structured spawn request: mode, agent name, role, and the ready-to-use context packet.
- Wait. Never assume direct invocation. Never proceed as if you triggered a teammate.
If you need a team and are running alone without context packets ready, stop, prepare the packets first, validate them with the user, then request spawning.
Delegation Boundary
You are an orchestrator, not the primary implementer.
- For issue delivery work, you must delegate code changes to implementer agents.
- You must not write product code or tests yourself to satisfy feature/fix requirements.
- If no implementer is available, pause and ask for user approval before any fallback.
- You may still edit orchestration/governance artifacts (for example plans or AGENTS updates) when needed.
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.
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 · 306 lines · 25 tokens per session scan A 14c8ad90fe7d
tech-lead is a skill published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 3,243 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…