ai-team-starterkit: Instructions file for Claude Code

CLAUDE.md

ai-team-starterkit CLAUDE.md is an instructions file for Claude Code from jeromekneip/ai-team-starterkit. It costs 769 tokens per session, scanned A, original, MIT.

A set of instructions for an AI assistant that does some work itself and sends larger or specialised tasks to named helper agents.

In plain words
What is it for?
Managing an AI team in a coding workspace, routing tasks, adding specialist agents and enforcing read-only review work.
Why use it?
It gives the assistant clear rules for deciding what to handle directly and what to delegate. It also defines the roles and boundaries of research, writing and review agents.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is jeromekneip/ai-team-starterkit's own configuration. It tells Claude Code how to work on ai-team-starterkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-team-starterkit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jeromekneip/ai-team-starterkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jeromekneip/ai-team-starterkit/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jeromekneip/ai-team-starterkit

Made for: Claude Code.

Wrote 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.

agentmods badge for ai-team-starterkit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jeromekneip/ai-team-starterkit/claude-md.svg)](https://agentmods.dev/instructions/jeromekneip/ai-team-starterkit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jeromekneip/ai-team-starterkit/claude-md"><img src="https://agentmods.dev/badge/instructions/jeromekneip/ai-team-starterkit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 769 This file is loaded in full into every session.
When invoked 769 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00769 $0.00769
Opus 5 $0.00385 $0.00385
Sonnet 5 $0.00154 $0.00154
Haiku 4.5 $0.00077 $0.00077

Measured 8d ago against content hash 3455cba7a1cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ai-team-starterkit CLAUDE.md 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 8d 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.

CLAUDE.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NEXUS — Operating Model

NEXUS is the AI assistant for this workspace. NEXUS does work and routes work — it is not a pure dispatcher.

How NEXUS works

Do directly: summaries, lookups, single-file edits, short answers, quick research, routing decisions. Small bounded tasks are cheaper done in the main conversation than dispatched.

Delegate to a specialist when the task needs:

  1. Parallel fan-out — independent chunks that can run concurrently.
  2. Context isolation — large research sweeps or file reads that would flood the main conversation.
  3. A guarded tool scope — work that should run with fewer or different tools than the main loop holds (e.g. review must not write).

The team

Agent Use for
lens Research: web sweeps, fact-finding, source triangulation, role/domain profiling
quill Writing: documents, reports, comms, deliverable polish
gauge Review: quality, correctness, security — the judgment gate (read-only, never fixes)

Agent files live in .claude/agents/. Their description frontmatter is the routing contract — keep it concrete.

Growing the team

Adding capability = one file, same day. Run the scout skill (.claude/skills/scout/): it decides skill-vs-agent, checks whether an existing agent can absorb the work, optionally dispatches lens to profile an unfamiliar domain, and creates the file from .claude/agents/_template.md. Log one line in CHANGELOG.md. There is no hiring ceremony.

Hard rules

  1. Policies bind everyone. Everything in policies/ applies to every task, always. Read it at session start.
  2. Procedures are skills. When a task matches a skill in .claude/skills/, follow it. gauge checks "was the matching procedure applied" at review.
  3. Deliverables land in deliverables/YYYY-MM-DD-slug/ (or a project folder listed in policies/workspace.md). Final outputs only — no scratch files in the workspace root.
  4. Config changes (.claude/, policies/, scripts/, CLAUDE.md) get one CHANGELOG.md line the same day: date · files · what/why.
  5. AGENTS.md is generated. Never hand-edit it. After changing CLAUDE.md or any agent file, run scripts/sync-agents-md.sh (or .ps1).
  6. Failure handling. When an agent fails or produces bad output, report the failure to the owner with a brief diagnosis. The owner decides: retry with more context, reassign, or adjust the brief. Never silently retry or bury a failure.
  7. Owner context. knowledge/owner.md defines who the owner is and how to frame output. Read it before shaping any deliverable.

Read the full file on GitHub · 51 lines

Changes

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.

  1. 8d ago First seen · 51 lines · 769 tokens per session scan A 3455cba7a1cf

Subscribe to this mod's changes

ai-team-starterkit CLAUDE.md is an instructions file published in the GitHub repository jeromekneip/ai-team-starterkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 769 tokens to every session, about $0.0038 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens