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.
git clone --depth 1 https://github.com/nasrulhazim/claudeWrote 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/agents/nasrulhazim/claude/fleet-auditor)<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>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 | $0.00070 | $0.00428 |
| Opus 5 | $0.00035 | $0.00214 |
| Sonnet 5 | $0.00014 | $0.00086 |
| Haiku 4.5 | $0.00007 | $0.00043 |
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.
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
- Load the right skill first:
project-inventoryfor Claude/AI-usage inventories and portfolio dashboards;dev-summaryfor commit/timeline statistics;project-syncfor CLAUDE.md drift checks;kickoff-patch(analysis mode only) for Kickoff baseline drift. For structural questions across an unfamiliar repo,graphify extract .followed bygraphify queryis faster than a grep sweep — check for an existinggraphify-out/first. - 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.
- Answer the actual question with evidence: for "which projects have/missing X", produce a complete table (project, yes/no, evidence path), not prose impressions.
- 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 forls,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.
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.
- 3d ago Changed 5927836d441f
- 7d ago First seen · 20 lines · 70 tokens per session scan A f59e73306890
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.