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 jeromekneip/ai-team-starterkit --skill scoutgit clone --depth 1 https://github.com/jeromekneip/ai-team-starterkitWrote 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/jeromekneip/ai-team-starterkit/scout)<a href="https://agentmods.dev/skills/jeromekneip/ai-team-starterkit/scout"><img src="https://agentmods.dev/badge/skills/jeromekneip/ai-team-starterkit/scout/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/jeromekneip/ai-team-starterkit/scout"><img src="https://agentmods.dev/badge/skills/jeromekneip/ai-team-starterkit/scout.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 | $0.00069 | $0.00768 |
| Opus 5 | $0.00034 | $0.00384 |
| Sonnet 5 | $0.00014 | $0.00154 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
scout 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 9d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SCOUT — Growing the Team
Adding capability is one file plus one changelog line, not a hiring ceremony. This procedure exists to make that file good.
Step 1 — Don't add: absorb
Read the existing agent files in .claude/agents/ first.
- If an existing agent could handle the work with ~60%+ expertise overlap, upgrade that agent (extend its Scope and Operating rules) instead of creating a new one. This is the cheaper, usually-right answer.
- If the need is a one-off, just do the task — capability files are for recurring needs.
Step 2 — Skill or agent?
- Skill (
.claude/skills/<name>/SKILL.md): the need is knowledge or procedure — a repeatable process, a domain checklist, a format standard. Most needs are skills. - Agent (
.claude/agents/<name>.md): the need is a distinct tool scope (fewer/different tools than the main loop), context isolation (big sweeps), or parallel work. Only then.
A new agent that differs from an existing one only in what it knows is a skill wearing a costume.
Step 3 — Research unfamiliar domains (optional but recommended)
If the capability covers a domain the team hasn't worked in, dispatch lens first with a research brief: what does a strong human practitioner in this role actually know, do, use, and refuse to do? Require from the profile:
- Core knowledge areas and working methods (triangulated, 3+ source types, year-stamped)
- The tacit judgment layer — what distinguishes a senior from a junior
- What a strong practitioner refuses to do
- Markers of excellence at edge cases, not just the happy path
Skip this only when the domain is already well understood in the workspace.
Step 4 — Write the file
- Agents: copy
.claude/agents/_template.mdand follow its embedded design checklist. - Skills: frontmatter
name+description(the description must contain concrete trigger phrases — it is what makes the skill load), then the procedure as a checklist. - Guidelines must be testable ("always X", "never Y"). If violating a rule causes no visible failure, it's decoration — cut it.
- No personas, no biographies, no static "watch lists" that freeze a year in time.
- Give the smallest tool scope that does the job.
model: inheritunless the role clearly needs a different tier.
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.
- 9d ago First seen · 54 lines · 69 tokens per session scan A 9a6e833c98e2
scout is a skill published in the GitHub repository jeromekneip/ai-team-starterkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 768 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…