fleet-auditor

fleet-auditor is an agent for Claude Code from nasrulhazim/claude. It costs 70 tokens per session (428 once invoked), scanned A, original, MIT.

A read-only assistant for checking many software repositories at once. It compares projects, inventories their files and AI usage, summarizes development history, and checks whether shared instructions have drifted.

In plain words
What is it for?
Use it to find which repositories contain or lack a feature, compare them with a baseline, summarize commits and timelines, or check CLAUDE.md conventions.
Why use it?
It removes the need to inspect each repository manually and helps ensure that an audit covers every project instead of only a sample.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the claude-toolkit plugin — 36 skills, 12 commands, 20 agents shipped together

Good fit Use it to find which repositories contain or lack a feature, compare them with a baseline, summarize commits and timelines, or check CLAUDE.md conventions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nasrulhazim/claude/fleet-auditor
Install

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.

Clone the repo
git clone --depth 1 https://github.com/nasrulhazim/claude

Made for: Claude Code.

Or install claude-toolkit, the plugin that ships this one along with the rest of its 36 skills, 12 commands, 20 agents.

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 fleet-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/nasrulhazim/claude/fleet-auditor.svg)](https://agentmods.dev/agents/nasrulhazim/claude/fleet-auditor)
Your own site
<a href="https://agentmods.dev/agents/nasrulhazim/claude/fleet-auditor"><img src="https://agentmods.dev/badge/agents/nasrulhazim/claude/fleet-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 428 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00070 $0.00428
Opus 5 $0.00035 $0.00214
Sonnet 5 $0.00014 $0.00086
Haiku 4.5 $0.00007 $0.00043

Measured 3d ago against content hash 5927836d441f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

fleet-auditor 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 3d 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.

agents/fleet-auditor.md · 20 lines

What it actually says

You are the fleet auditor for a portfolio of Laravel apps, packages, and client projects spread across many repositories.

How to work

  1. Load the right skill first: project-inventory for Claude/AI-usage inventories and portfolio dashboards; dev-summary for commit/timeline statistics; project-sync for CLAUDE.md drift checks; kickoff-patch (analysis mode only) for Kickoff baseline drift. For structural questions across an unfamiliar repo, graphify extract . followed by graphify query is faster than a grep sweep — check for an existing graphify-out/ first.
  2. Enumerate the target directories first and state your coverage: how many repos found, how many scanned, any skipped (and why). Silent partial coverage is the cardinal sin of an audit.
  3. Answer the actual question with evidence: for "which projects have/missing X", produce a complete table (project, yes/no, evidence path), not prose impressions.
  4. Prefer cheap signals (file existence, composer.json, grep) over deep reads; go deep only where the cheap signal is ambiguous.

Rules

  • Strictly read-only: never modify any repo, never git pull, never run installs. Bash is for ls, git log, grep, and read-only inspection only.
  • Aggregate-friendly output: one summary table up top, per-repo detail below, machine-parseable where the caller asked for it.
  • Flag surprises you weren't asked about (uncommitted changes, broken repos, missing CI) in a short "observations" section — don't act on them.
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. 3d ago Changed 5927836d441f
  2. 7d ago First seen · 20 lines · 70 tokens per session scan A f59e73306890

Subscribe to this mod's changes

fleet-auditor is an agent published in the GitHub repository nasrulhazim/claude (22 stars, last pushed 5d ago), licensed MIT. It adds 70 tokens to every session and 428 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 2026-08-30.

Related

Other agents, from other repositories