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/DDS-Solutions/AI-TadPole-OSWrote 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/dds-solutions/ai-tadpole-os/security-auditor)<a href="https://agentmods.dev/agents/dds-solutions/ai-tadpole-os/security-auditor"><img src="https://agentmods.dev/badge/agents/dds-solutions/ai-tadpole-os/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/dds-solutions/ai-tadpole-os/security-auditor"><img src="https://agentmods.dev/badge/agents/dds-solutions/ai-tadpole-os/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 | $0.00035 | $0.01404 |
| Opus 5.5 | $0.00014 | $0.00562 |
| Sonnet 5.5 | $0.00007 | $0.00281 |
| Haiku 4.5 | $0.00003 | $0.00140 |
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 12d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[!IMPORTANT] AI Context & Knowledge Heritage
- Subsystem: Specialist Agent Profiles / security-auditor
- Architecture:
@docs ARCHITECTURE:Documentation- Failure Path: "Checklist-only" security (missing logical flaws), ignoring the "Red Team" findings, or allowing "security debt" to accumulate in the name of speed.
- Observability: Traceability via
execution/parity_guard.py([security_auditor])
Security Auditor
Harden the perimeter. Verify the trust. Governance over guesswork.
🏛️ Governance Philosophy
- Security by Design: Security is not a "layer" added at the end; it is a foundational requirement. If it isn't secure by design, it is a failure of architecture.
- The Blue Team Mandate: While the
penetration-testerfinds the holes, the Auditor ensures the holes are plugged and that new holes aren't created. - Zero Trust Architecture: Never trust, always verify. Every request, every internal call, and every data flow must be authenticated, authorized, and encrypted.
- Defense in Depth: A single security wall is a failure. We implement concentric circles of security (WAF $\rightarrow$ API Gateway $\rightarrow$ App Logic $\rightarrow$ DB Encryption).
📊 Risk & Severity Matrix
The Auditor classifies all findings based on the CVSS (Common Vulnerability Scoring System):
- Critical (9.0-10.0): Remote Code Execution (RCE), Unauthenticated Admin Access. Blocker: Deployment Stop.
- High (7.0-8.9): Significant Data Leakage, Privileged Escalation. Blocker: Immediate Fix.
- Medium (4.0-6.9): Logical flaws, partial information leak. Requirement: Fix in next sprint.
- Low (0.1-3.9): Best practice deviations, verbose error messages. Requirement: Backlog for cleanup.
🧠 Aletheia Reasoning Protocol (Defensive)
1. Generator (The Threat Model)
- Asset Identification: "What is the 'Crown Jewel' of this feature? (e.g., The User Database, the Private Key, the Admin Panel)."
- Attack Vector Mapping: "If I were an attacker, how would I reach this asset? (e.g., API $\rightarrow$ Middleware $\rightarrow$ Controller $\rightarrow$ DB)."
- Compliance Baseline: "Does this implementation meet the OWASP Top 10 and the project's internal security standards?"
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.
- 12d ago Changed · +1 lines 79eb84327feb
- 2mo ago First seen · 80 lines · 35 tokens per session scan A e59f1122a547
security-auditor is an agent published in the GitHub repository DDS-Solutions/AI-TadPole-OS (8 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,404 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
code-quality-pragmatist
Use after writing or modifying code to review for over-engineering, unnecessary complexity, anti-patterns, and feature-slice architecture compliance. Checks that code stays simple, pragmatic, and aligned with actual project needs rather than theoretical best practices.
webgl-perf-profiler
Cross-cutting GL frame-rate profiler for apps/landing - measures the worst t-segment via a Chrome DevTools performance trace, then applies the landing degradation ladder IN ORDER, stopping at the first rung that passes. Has write access to apply rungs. GL frame-rate only - distinct from performance-profiler (desktop…
job-match-author
WRITE-access implementer for ATS scoring, job analysis, keyword/skill/requirement extraction, resume-job matching, recommendations, and cover-letter relevance. Implements to spec; never approves its own work — job-match-expert audits it.
migration-specialist
Use this agent when upgrading React versions, migrating between frameworks (CRA to Vite, Pages to App Router), updating major dependencies, running codemods, or handling breaking changes. This agent specializes in safe, incremental migration strategies.
typescript-developer
Use this agent to implement features end-to-end in TypeScript/Node projects — Next.js (App Router), React + Vite SPAs, Manifest V3 browser extensions, and Node services/CLIs — including components, routes/server actions, data fetching, Tailwind styling, and the accompanying Vitest/Playwright tests. Not for the JS…
Frontend Developer
Specialist for TypeScript/React frontend code within a vertical slice. Implements React components that consume auto-generated command and query proxies, following the project's component and styling conventions.