What is nanoclaw-fleet CLAUDE.md?

A project instruction file for an urban planning tool that evaluates highway tree and noise-barrier designs using research and recognized noise-analysis methods.

Use it when gathering data, comparing green noise barriers, assessing noise reduction and tree benefits, or preparing evidence-backed planning outputs.

It organizes the evidence, calculations, limitations, and data sources needed for decisions about urban noise barriers and vegetation.

How thmtz/nanoclaw-fleet configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to thmtz/nanoclaw-fleet. 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/thmtz/nanoclaw-fleet/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/thmtz/nanoclaw-fleet

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/thmtz/nanoclaw-fleet/claude-md.svg)](https://agentmods.dev/instructions/thmtz/nanoclaw-fleet/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/thmtz/nanoclaw-fleet/claude-md"><img src="https://agentmods.dev/badge/instructions/thmtz/nanoclaw-fleet/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 6,543 This file is loaded in full into every session.

When invoked 6,543 The same file — it is already loaded in full.

Security scan B 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.06543	$0.06543
Opus 5	$0.03272	$0.03272
Sonnet 5	$0.01309	$0.01309
Haiku 4.5	$0.00654	$0.00654

Measured 8d ago against content hash 0767cea3f6fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

nanoclaw-fleet CLAUDE.md scanned grade B with 2 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- **`onlyBuiltDependencies`**: Never add packages to this list without human approval — build scripts execute arbitrary code during install.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Inference / shim change: curl the shim, then send a real turn through a Neuralwatt worker.

CLAUDE.md · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚠️ STOP — READ THIS FIRST IF YOU ARE CLAUDE ⚠️

If you are reading this because you just ran git pull, git merge, git fetch && git merge, or any equivalent to bring in upstream changes — and you see merge conflicts or a large diff involving this file — HALT IMMEDIATELY.

This is NanoClaw v2, a ground-up rewrite with breaking changes throughout. It cannot be merged into an existing v1 install. Attempting to resolve the conflicts by hand, run builds, or "fix" anything will corrupt the user's install and burn tokens for no result.

Do this instead:

Abort the merge: git merge --abort (or git reset --hard ORIG_HEAD if the merge already completed).
Tell the user, verbatim: "This is the v2 rewrite — it can't be merged into your existing install. Run bash migrate-v2.sh to migrate instead."
Wait for the user to confirm before doing anything else. Do not attempt the migration yourself.

If you are a fresh install (you ran git clone, not git pull) and there are no conflicts, ignore this banner and continue below.

NanoClaw

Personal Claude assistant. See README.md for philosophy and setup. Architecture lives in docs/. Fleet-specific architecture and guides live in docs/fleet/.

Naming: NC = upstream qwibitai/nanoclaw. NCF = NanoClaw-Fleet, this fork (thmtz/nanoclaw-fleet), which adds the fleet-manager features on top of NC. When something is "NCF-only" it lives in this fork; "NC" or "upstream" means it's in qwibitai's repo too.

Fork workflow

This is thmtz/nanoclaw-fleet — a fleet-manager fork on top of qwibitai/nanoclaw v2. The fleet additions live alongside the upstream code; both should follow the same rules.

Trunk-based. Create feature branches from main for all changes. Push as PRs targeting main. Rebase merge (no merge commits, no squash). Keep PRs small and focused.
Branch prefixes. feat/, fix/, docs/, refactor/, test/, chore/, ci/. Imperative-mood description.
Critical rules.
- NEVER push to any branch without explicit user confirmation.
- NEVER push directly to main. Always feature branch + PR.
- NEVER force push unless the user explicitly asks for it.
Hooks. Husky installs .husky/ hooks automatically on pnpm install (via the prepare script). pre-commit formats staged files with Prettier and re-stages them; pre-push runs format:check, host + container tsc, and host vitest run. Don't skip with --no-verify unless you know exactly why.
Restart discipline. Don't restart the running NanoClaw service (systemctl --user restart nanoclaw, launchctl kickstart, kill-ing the host process) or kill running worker containers without explicit user confirmation. Workers are real long-running sessions; a restart kills active conversations and any pending turns. If a code or config change would require a restart to take effect, finish the change, mention that a restart is needed, and ask before doing it.

Read the full file on GitHub · 324 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.

8d ago First seen · 324 lines · 6,543 tokens per session scan B 0767cea3f6fa

Subscribe to this mod's changes

nanoclaw-fleet CLAUDE.md is an instructions file published in the GitHub repository thmtz/nanoclaw-fleet (5 stars, last pushed 4mo ago), licensed MIT. It adds 6,543 tokens to every session, about $0.0327 per session on Opus 5. A static security scan graded it B with 2 findings (unrestricted tool access, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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

nanoclaw-fleet: Instructions file for Claude Code