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.
curl -O https://raw.githubusercontent.com/jeromekneip/ai-team-starterkit/main/CLAUDE.mdgit 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/instructions/jeromekneip/ai-team-starterkit/claude-md)<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>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 | $0.00769 | $0.00769 |
| Opus 5 | $0.00385 | $0.00385 |
| Sonnet 5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
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.
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:
- Parallel fan-out — independent chunks that can run concurrently.
- Context isolation — large research sweeps or file reads that would flood the main conversation.
- 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
- Policies bind everyone. Everything in
policies/applies to every task, always. Read it at session start. - Procedures are skills. When a task matches a skill in
.claude/skills/, follow it.gaugechecks "was the matching procedure applied" at review. - Deliverables land in
deliverables/YYYY-MM-DD-slug/(or a project folder listed inpolicies/workspace.md). Final outputs only — no scratch files in the workspace root. - Config changes (
.claude/,policies/,scripts/,CLAUDE.md) get oneCHANGELOG.mdline the same day: date · files · what/why. AGENTS.mdis generated. Never hand-edit it. After changingCLAUDE.mdor any agent file, runscripts/sync-agents-md.sh(or.ps1).- 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.
- Owner context.
knowledge/owner.mddefines who the owner is and how to frame output. Read it before shaping any deliverable.
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.
- 8d ago First seen · 51 lines · 769 tokens per session scan A 3455cba7a1cf
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.
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.
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.
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).
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).
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.
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.