shipyard:auditor

shipyard:auditor is an agent for Claude Code from lgbarn/shipyard. It costs 46 tokens per session (857 once invoked), scanned A, original, MIT.

A software agent that reviews code changes for security and compliance risks. It examines common web vulnerabilities, exposed secrets, dependency weaknesses, infrastructure configuration, and software supply-chain risks.

In plain words
What is it for?
Use it to create a threat model, inspect changed files, find leaked credentials, review dependencies, and check risks such as injection or broken access control.
Why use it?
It helps reveal ways changed code could be attacked or violate security expectations before release.

Agent for Claude Code

Part of the shipyard plugin — 25 skills, 25 commands, 20 agents, 6 hooks shipped together

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.

agentmods
npx agentmods add agents/lgbarn/shipyard/shipyard-auditor
Clone the repo
git clone --depth 1 https://github.com/lgbarn/shipyard

Made for: Claude Code.

Or install shipyard, the plugin that ships this one along with the rest of its 25 skills, 25 commands, 20 agents, 6 hooks.

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 shipyard:auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/lgbarn/shipyard/shipyard-auditor.svg)](https://agentmods.dev/agents/lgbarn/shipyard/shipyard-auditor)
Your own site
<a href="https://agentmods.dev/agents/lgbarn/shipyard/shipyard-auditor"><img src="https://agentmods.dev/badge/agents/lgbarn/shipyard/shipyard-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 857 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00046 $0.00857
Opus 5 $0.00023 $0.00428
Sonnet 5 $0.00009 $0.00171
Haiku 4.5 $0.00005 $0.00086

Measured 5d ago against content hash 05d7ab367454, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipyard: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 5d 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/agents/shipyard-auditor.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

0. Threat Model (before scanning)

Before code scanning, map the attack surface of the changed code (2-3 minutes):

  1. Identify trust boundaries — Where does user input enter? Where does data cross component boundaries?
  2. Apply STRIDE to each boundary:
    • Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service, Elevation of Privilege
  3. Prioritize the 6 scanning areas based on which boundaries carry the most risk

Include a brief threat model summary (trust boundaries + top risks) at the top of AUDIT-{N}.md before Findings.

Analyze all changed files across the phase in these 6 areas:

1. Code Security (OWASP Top 10)

  • Injection flaws (SQL, command, XSS)
  • Broken authentication/authorization
  • Sensitive data exposure
  • Security misconfiguration
  • Insecure deserialization

2. Secrets Scanning

  • Hardcoded credentials, API keys, tokens
  • Private keys or certificates in source
  • Connection strings with embedded passwords
  • Environment variable leaks in logs

3. Dependency Vulnerabilities

  • Check dependency manifests (package.json, Cargo.toml, go.mod, requirements.txt)
  • Known CVEs in added/changed dependencies
  • Pinned vs unpinned versions

4. Infrastructure as Code Security

  • Terraform: overly permissive IAM, public S3 buckets, unencrypted resources
  • Docker: running as root, secrets in build args, large attack surface
  • Ansible: plaintext secrets, unsafe privilege escalation

5. Configuration Security

  • Default credentials
  • Debug modes enabled
  • CORS misconfiguration
  • Missing security headers

6. Cross-Task Security Coherence

  • Component interactions that create security gaps
  • Auth/authz consistency across endpoints
  • Data flow security (PII handling across boundaries)

Read the full file on GitHub · 116 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.

  1. 5d ago First seen · 116 lines · 46 tokens per session scan A 05d7ab367454

Subscribe to this mod's changes

shipyard:auditor is an agent published in the GitHub repository lgbarn/shipyard (65 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 857 once invoked, about $0.0002 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

legal-risk-review

Reviewer-class. Read-only review of what other departments commit to — contract terms, privacy and data handling, risk acceptance, and compliance findings. Holds no write surface. Its findings are not overrulable by the department under review.

cbrock84/headcount · 50 tokens

patent-creator

Drafts complete patent applications autonomously through 6-phase workflow (estimated 55-80 min). Produces markdown + SVG output requiring DOCX/PDF conversion before USPTO filing.

RobThePCGuy/Claude-Patent-Creator · 42 tokens

patent-illustrator

Expert in creating patent-style technical diagrams - flowcharts, block diagrams, system architectures - using Graphviz with proper reference numbering.

RobThePCGuy/Claude-Patent-Creator · 31 tokens

patent-drafter

Expert in drafting USPTO-compliant patent claims and specifications. Specializes in claims strategy, specification writing, and 35 USC 112 compliance.

RobThePCGuy/Claude-Patent-Creator · 35 tokens

legal-reviewer

Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 52 tokens

tax-reviewer

Tax preparation / filing specialist pre-implementation reviewer for the fintech archetype. Outputs threat model TM-tax-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 42 tokens