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.
npx skills add sethdford/claude-skills --skill system-auditgit clone --depth 1 https://github.com/sethdford/claude-skillsWrote 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/skills/sethdford/claude-skills/system-audit)<a href="https://agentmods.dev/skills/sethdford/claude-skills/system-audit"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/system-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.
<a href="https://agentmods.dev/skills/sethdford/claude-skills/system-audit"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/system-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00028 | $0.00763 |
| Opus 5 | $0.00014 | $0.00381 |
| Sonnet 5 | $0.00006 | $0.00153 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
system-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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Audit
Conduct comprehensive evaluation of system architecture and identify improvement opportunities.
Context
You are auditing a system's architecture. Assess design quality, technical debt, operational readiness, scalability potential. Read code, infrastructure, metrics, team feedback.
Domain Context
Based on architecture assessment frameworks:
- Design Quality: Modularity, coupling, cohesion. Is architecture aligned with business domains? Easy to change?
- Operational Readiness: Monitoring, alerting, logging, runbooks. Can ops team run this effectively? What happens when it fails?
- Scalability: Can it handle 10x growth? What's the bottleneck? Vertical or horizontal scaling?
- Technical Debt: What's slowing teams down? What would refactoring improve?
- Security and Compliance: Data protection, access control, audit trails, regulatory alignment?
Instructions
-
Prepare Audit Checklist:
- Architecture & Design (modularity, coupling, domain alignment)
- Data (model, storage, flow, governance)
- Scalability (bottlenecks, growth headroom)
- Operations (monitoring, logging, alerting, runbooks)
- Security & Compliance (data protection, access control, audit)
- Team Productivity (deployment time, testing capability, cycle time)
-
Gather Information:
- Read architecture documentation, design documents
- Review code structure, dependencies
- Check infrastructure-as-code, deployment pipelines
- Interview team: "What's hard? What's slow? What worries you?"
- Review metrics: latency, error rate, utilization, deployment frequency
-
Assess Each Area:
- Score: Good (no action needed), Fair (monitor, improve over time), Poor (urgent)
- Document evidence: "Monolith 500K lines, 30-min builds, hard to test"
-
Identify Patterns:
- Common themes? Multiple "poor" scores suggest systemic issues.
- Root causes: "Tight coupling causing hard deployments and scaling issues"
-
Recommend Improvements:
- Prioritize by impact and effort
- Quick wins (low effort, high impact): improve monitoring, document runbooks
- Strategic initiatives (high effort, high impact): decompose monolith, refactor critical paths
- Timeline: what's urgent vs 2-year plan?
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.
- 9d ago First seen · 73 lines · 28 tokens per session scan A 4c6f94f97bb3
system-audit is a skill published in the GitHub repository sethdford/claude-skills (40 stars, last pushed 6mo ago), licensed MIT. It adds 28 tokens to every session and 763 once invoked, about $0.0001 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 skills, from other repositories
cmd_flutter_build
Fix Dart analyzer errors and Flutter build failures incrementally. Invokes the dart-build-resolver agent for minimal, surgical fixes.
cmd_hookify
Create OpenClaw hook rules to prevent unwanted agent behaviors.
cmd_cpp_build
Fix C++ build errors, CMake issues, and linker problems incrementally. Invokes the cpp-build-resolver agent for minimal, surgical fixes.
cmd_go_build
Fix Go build errors, go vet warnings, and linter issues incrementally. Invokes the go-build-resolver agent for minimal, surgical fixes.
cmd_gradle_build
Fix Gradle build errors for Android and KMP projects.
cmd_build_fix
Incrementally fix build and type errors with minimal, safe changes. Detects build system, parses errors, and fixes one at a time.