A process for publishing automated audit findings to GitHub, a code-hosting and collaboration service. Each audit stream gets one continuously updated issue, while repository fixes are proposed separately as focused pull requests for review.

Use it to create or update audit issues, track changes between audit runs, close clean audit streams, and prepare narrowly scoped pull requests linked to the findings.

It keeps recurring findings in one durable, de-duplicated record instead of scattering them across chat messages. Separating reports from code changes makes each easier to review.

fleet-audit — Skill for Claude Code and Codex by gke-labs/kube-agents

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.

Any agent

npx skills add gke-labs/kube-agents --skill fleet-audit

Clone the repo

git clone --depth 1 https://github.com/gke-labs/kube-agents

Made for: Claude Code, Codex.

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/skills/gke-labs/kube-agents/fleet-audit/github.svg)](https://agentmods.dev/skills/gke-labs/kube-agents/fleet-audit)

Your own site

<a href="https://agentmods.dev/skills/gke-labs/kube-agents/fleet-audit"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/fleet-audit/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/skills/gke-labs/kube-agents/fleet-audit"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/fleet-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,128 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00044	$0.04128
Opus 5.5	$0.00018	$0.01651
Sonnet 5.5	$0.00009	$0.00826
Haiku 4.5	$0.00004	$0.00413

Measured yesterday against content hash 2bb50e52a0a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fleet-audit 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 yesterday.

The scan reads SKILL.md. This mod also ships 18 executable files (scripts/audit_report.py, scripts/collect.py, scripts/fleet_drift.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/platform/skills/fleet-audit/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fleet-audit — Audit Findings to a Ledger Issue

Every autonomous audit watchdog ends the same way: findings must reach a human somewhere durable, reviewable, and de-duplicated. This skill is that ending, in two tiers:

Tier 1 — the ledger. Each audit stream owns exactly one open issue on the forge, rewritten in full on every run and closed as completed when the fleet comes back clean. An operator watches one issue per stream instead of drowning in chat logs.
Tier 2 — the fixes. When a finding's remediation is a file in this repository, it travels separately as a narrow pull request carrying only that fix, linked back to the ledger.

The split is the point. A report is not a change, so a report is not a pull request — and a fix is not a report, so it carries a real diff a reviewer can read in one screen.

/opt/data/profiles/platform/skills/fleet-audit/scripts/audit_report.py owns every deterministic operation: credential minting, label creation, issue creation and rewriting, branch handling, staging, committing, pushing, pull-request creation, closing, the run-over-run delta, and every timestamp. Your job is to inspect the fleet read-only and emit a findings.json. You never hand-write an issue body or a PR body, never invent a timestamp, and never open an issue or pull request yourself — not with vcs.py issue create or vcs.py proposal create, and not any other way — that is precisely why every ledger looks the same and why the delta between runs is computable.

Audit streams

Only these registered audit ids may own a ledger. Any other id is rejected before a single git or forge operation runs. The issue title is [audit] <human name> — <n> findings (<c> critical) (singular 1 finding when there is exactly one), where the human name is the one cron/jobs.json gives that watchdog — not a prettified form of the audit id:

Audit id	Rendered ledger title
`compliance-audit`	`[audit] Security & RBAC Posture Audit — 7 findings (2 critical)`
`security-patch-orchestrator`	`[audit] Upgrade & Patch Readiness Audit — 7 findings (2 critical)`
`obtainability-audit`	`[audit] Workload Reliability Audit — 7 findings (2 critical)`
`fleet-wide-cost-analysis`	`[audit] Fleet Waste Audit — 7 findings (2 critical)`
`fleet-consistency-drift`	`[audit] Fleet Consistency Drift Audit — 7 findings (2 critical)`
`ai-security-audit`	`[audit] AI Workload Security Audit — 7 findings (2 critical)`
`stockout-prevention`	`[audit] Fleet Stockout Prevention & Capacity Audit — 7 findings (2 critical)`
`gcp-networking-fabric-audit`	`[audit] GCP Networking Fabric & VPC IPAM Audit — 7 findings (2 critical)`
`gce-compute-fleet-audit`	`[audit] GCE Compute Engine and MIG Fleet Audit — 7 findings (2 critical)`
`upgrade-retrospective`	`[audit] Upgrade Retrospective — 7 findings (0 critical)`

Read the full file on GitHub · 218 lines

Files

What ships with it

54 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

yesterday Changed · +3 lines 2bb50e52a0a0
4d ago Changed · +1 lines 60ae81190ec6
6d ago Changed · +6 lines cd963fdd1ad6
7d ago Changed · +6 lines 1d97188f410b
11d ago Changed · -1,228 lines 220d06babafb
12d ago Changed · +24 lines 7037f72948d7
13d ago Changed · +35 lines de54ac22a91b
14d ago Changed · +5 lines 54aa76c17340
15d ago Changed · +18 lines fa1ddaf7f9b5
18d ago First seen · 1,348 lines · 44 tokens per session scan A b5f4bca08bb1

Subscribe to this mod's changes

fleet-audit is a skill published in the GitHub repository gke-labs/kube-agents (116 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 4,128 once invoked, about $0.0002 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.

Code review Project management

tech-debt

Track, categorize and prioritize technical debt across the codebase — scans for debt indicators, maintains a register.

Donchitos/Claude-Code-Game-Studios · 25 tokens

OpenSourceManagement

Triages open issues, pull requests and GitHub Discussions across the principal's own open-source repos (the list in Config.md) via the gh CLI, ranks what needs attention with suggested replies, posts edit-in-place marker comments, diffs new Ollama library models against a local model box, and takes a private repo…

danielmiessler/LifeOS · 212 tokens

pr-review-triage

Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.

cobusgreyling/loop-engineering · 35 tokens

issue-creation

Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.

Gentleman-Programming/gentle-ai · 30 tokens

systemic-issue-triage

Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.

Gentleman-Programming/gentle-ai · 57 tokens

spec-kitty-runtime-review

Review runtime-owned outputs using the Spec Kitty review workflow surface, then direct approval or rejection with structured feedback. Triggers: "review this work package", "check runtime output", "approve this step", "review WP", "is this WP ready to approve", "check this implementation". Does NOT handle: setup-only…

Priivacy-ai/spec-kitty · 85 tokens