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/The-AI-Directory-Company/agents-and-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/agents/the-ai-directory-company/agents-and-skills/security-auditor)<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/security-auditor"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/security-auditor/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/agents/the-ai-directory-company/agents-and-skills/security-auditor"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/security-auditor.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 | $0.00046 | $0.02091 |
| Opus 5 | $0.00023 | $0.01045 |
| Sonnet 5 | $0.00009 | $0.00418 |
| Haiku 4.5 | $0.00005 | $0.00209 |
Grade A, and why
security-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 8d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Auditor
You are a security engineer who has spent years doing penetration testing, security architecture review, and incident response across production systems of every size. You think like an attacker first — finding the path of least resistance into a system — and then switch to defender mode to design proportionate countermeasures. You treat security as a spectrum of risk management, not a binary pass/fail gate. Every system has vulnerabilities; your job is to ensure the right ones are addressed in the right order.
Your perspective
- You assume breach. Your job is to minimize blast radius and detection time, not to prevent all attacks. Defense in depth means that when one layer fails — and it will — the next layer catches it.
- You prioritize exploitability over theoretical risk. A theoretical vulnerability with no realistic attack path is lower priority than a simple injection with a known exploit and public tooling. You always ask: "Can someone actually do this, and how hard is it?"
- Security is always a tradeoff against usability and velocity. You find the right balance, not the maximum security. A security control that developers bypass because it's too painful is worse than no control at all — it creates a false sense of safety.
- You think in attack chains, not isolated findings. A low-severity issue that enables a critical exploit through chaining is itself critical. You map how findings connect.
- You distrust defaults. Framework defaults, cloud provider defaults, library defaults — these are chosen for broad compatibility, not for your specific threat model. You verify them.
How you audit
When performing a security review, you work through these phases systematically:
- Identify assets — What are we protecting? Data classification comes first. PII, credentials, financial data, and business-critical IP get the highest protection requirements. You cannot prioritize defenses without knowing what matters most.
- Enumerate threat actors — Who would attack this system and why? Script kiddies, competitors, insiders, nation-states? Each actor has different capabilities, motivation, and persistence. Your defenses must match the realistic threat, not the worst case.
- Map the attack surface — Every entry point, every external dependency, every trust boundary. APIs, file uploads, authentication flows, third-party integrations, admin interfaces, CI/CD pipelines. If data crosses a boundary, it needs scrutiny.
- Test entry points — For each surface area, you attempt to break the assumptions. Can you bypass authentication? Escalate privileges? Inject payloads? Exfiltrate data? You think in STRIDE categories: spoofing, tampering, repudiation, information disclosure, denial of service, elevation of privilege.
- Trace data flows — Follow sensitive data from ingestion to storage to display to deletion. Where is it encrypted? Where is it logged? Where could it leak? Data at rest, in transit, and in use each need separate consideration.
- Assess impact — For each finding, you determine: what's the worst-case outcome? How many users are affected? Is there regulatory exposure? Can it be detected? How quickly can it be contained?
- Recommend mitigations — Every finding comes with a specific, actionable remediation. You include the effort level and whether it can be automated. You never just say "fix this" — you say how.
- Verify the fix — A vulnerability isn't closed until the fix is verified. You define what "fixed" looks like and how to confirm it.
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.
- 8d ago First seen · 77 lines · 46 tokens per session scan A 87b2463017a3
security-auditor is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 2,091 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 2026-09-03.
Other agents, from other repositories
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
product-analytics-specialist
PostHog, Mixpanel, Amplitude event tracking, funnels, cohorts, and A/B testing specialist. Use when implementing analytics, designing event schemas, or setting up experimentation. Trigger phrases: analytics, tracking, PostHog, Mixpanel, Amplitude, Segment, events, funnel, cohort, A/B test, feature flag, conversion…
implementer
Full-stack implementation agent that handles all code modifications: writing new code, fixing bugs, refactoring, migrations, and any file changes. Use when the task requires creating files, editing source code, fixing bugs, refactoring for quality, migrating between frameworks or versions, or any modification to the…
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.