What is alloy-fleet-manager CLAUDE.md?

A project instruction file for an AI coding assistant working on the Alloy Fleet Manager repository. It records the project’s purpose, layout, technology choices, rules, and how to recover context between conversations.

Use it when starting work, handing a task to another assistant, or recovering after a conversation becomes too long. It helps with editing the right parts of the repository and following its development and release practices.

It gives the assistant the background needed to continue work without rereading the entire repository or an earlier conversation. This helps keep changes aligned with the project’s rules and structure.

How danielfree19/alloy-fleet-manager configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to danielfree19/alloy-fleet-manager. 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/danielfree19/alloy-fleet-manager/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/danielfree19/alloy-fleet-manager

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/danielfree19/alloy-fleet-manager/claude-md/github.svg)](https://agentmods.dev/instructions/danielfree19/alloy-fleet-manager/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/danielfree19/alloy-fleet-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/danielfree19/alloy-fleet-manager/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/danielfree19/alloy-fleet-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/danielfree19/alloy-fleet-manager/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,333 This file is loaded in full into every session.

When invoked 5,333 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.

Model	Per session	Once invoked
Fable 5.1	$0.05333	$0.05333
Opus 5.5	$0.02133	$0.02133
Sonnet 5.5	$0.01067	$0.01067
Haiku 4.5	$0.00533	$0.00533

Measured 2mo ago against content hash b4afc13e5635, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

alloy-fleet-manager 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 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.

CLAUDE.md · 453 lines

How it starts

The opening of the file, as written. The whole thing — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Handoff & Context Recovery

Purpose: When the conversation context is close to its limit and we need to start fresh (or hand off mid-task), read this file FIRST. It's the cheapest way back into the project's mental model — much cheaper than re-reading the whole repo or the prior transcript.

Last updated: 2026-04-25 (Phase 2 SSO — OIDC delivered; open-source release plumbing landed: Apache-2.0 LICENSE, CONTRIBUTING/SECURITY/COC/MAINTAINERS, GitLab CI pipeline, GoReleaser configs for the Terraform provider + fleetctl, npm publish wiring for @fleet-oss/sdk, multi-arch Docker buildx, automated GitHub mirror push. See docs/ci-cd.md and docs/release.md. Security hardening pass — @fastify/helmet (strict CSP + frame-ancestors 'none' + HSTS), @fastify/rate-limit on /auth/login and /auth/sso/start/:id, per-account lockout (5 failures / 15 min, audited as auth.login.locked + admin-clear via PATCH /users/:id { unlock: true } → user.unlock), pino redaction of auth headers + body fields, recordAuditEvent deny-list sanitizer, OIDC SSRF guard (auth/sso/url-guard.ts: pre-flight + custom lookup into openid-client via custom.setHttpOptionsDefaults). First test harness — vitest in apps/fleet-manager (npm run test -w apps/fleet-manager).).

0. Hard rules (from the user, must follow)

These came from <user_rules> and apply to every change you make:

Prefer Node.js + Go. This is the polyglot baseline; don't introduce Python/Rust/etc. without explicit user approval.
Document everything you do and document app functionality. After any non-trivial change update the relevant docs/*.md (and this file when scope shifts). README links are the table of contents.
Don't rewrite code without checking that you don't cancel old logic. Old code paths are often deliberately preserved (e.g. the legacy agent, the legacy AGENT_BEARER_TOKEN path). Read the surrounding code and any preceding docs before deleting or replacing.

Read the full file on GitHub · 453 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.

2mo ago First seen · 453 lines · 5,333 tokens per session scan A b4afc13e5635

Subscribe to this mod's changes

alloy-fleet-manager CLAUDE.md is an instructions file published in the GitHub repository danielfree19/alloy-fleet-manager (23 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 5,333 tokens to every session, about $0.0213 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 2026-08-30.

alloy-fleet-manager CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
alloy-fleet-manager CLAUDE.mddanielfree19/alloy-fleet-manager	Instructions file	23	6mo ago	Apache-2.0	A	5,333	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

alloy-fleet-manager: Instructions file for Claude Code