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 MSApps-Mobile/claude-plugins --skill sosa-auditgit clone --depth 1 https://github.com/MSApps-Mobile/claude-pluginsWrote 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/msapps-mobile/claude-plugins/sosa-audit)<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/sosa-audit"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/sosa-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/msapps-mobile/claude-plugins/sosa-audit"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/sosa-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 | $0.00000 | $0.02442 |
| Opus 5.5 | $0.00000 | $0.00977 |
| Sonnet 5.5 | $0.00000 | $0.00488 |
| Haiku 4.5 | $0.00000 | $0.00244 |
Grade A, and why
sosa-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 1mo 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SOSA Compliance Audit
Objective
Conduct comprehensive SOSA™ (Supervised Orchestrated Secured Agents) compliance assessment across your AI operations infrastructure and software engineering workflows. This skill audits adherence to the four SOSA pillars — for both enterprise agent operations and AI-assisted code generation — and identifies remediation actions needed to achieve target compliance levels.
Context
SOSA compliance ensures production-grade autonomous AI operations through four interdependent pillars:
- Supervised: Graduated human oversight calibrated to action impact
- Orchestrated: Coordinated multi-agent workflows with structured context sharing
- Secured: Zero-trust security with scoped permissions and immutable audit trails
- Agents: Formally specified autonomous entities with defined roles, tools, memory, and planning policies
Compliance is assessed at three levels:
- Level 1 (70%): Basic compliance with foundational controls
- Level 2 (85%): Intermediate compliance with enhanced monitoring and automated controls
- Level 3 (100%): Advanced compliance with continuous monitoring and automated enforcement
Plan Phase
Step 1: Define Scope
- Identify target systems, plugins, skills, scheduled tasks, and code repositories
- Document audit objectives and success criteria
- Establish baseline compliance expectations
- Determine impact level (low/medium/high) per component
- Identify whether audit covers operations, code, or both domains
Step 2: Checklist Selection
- Review SOSA compliance checklist (see
references/sosa-checklist.md) - Select controls relevant to the environment
- Prioritize critical vs. nice-to-have controls
- Map controls to SOSA pillars
- For code audits: include code-specific supervision levels, trust gradient, and Plan-Code-Verify controls
Step 3: Assessment Approach
- Plan data collection methods (file scanning, config review, log analysis)
- Identify required access levels
- Define timeline and resource allocation
- Prepare stakeholder communication
What ships with it
1 file 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.
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.
- 1mo ago First seen · 182 lines · 0 tokens per session scan A 795ca0505548
sosa-audit is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,442 tokens. 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 2026-09-13.
Other skills, from other repositories
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
media-gemini-3-image-prompt
A prompt builder for Gemini 3 Pro Image, also known as Nano Banana Pro, Google's image-generation model. It expands a short request into five parts covering the subject, action, setting, composition, lighting, style, and text constraints.
data-realestate
A lookup tool for reported South Korean property transactions using Ministry of Land data. It covers sales and rental deals for apartments, officetels, multi-family homes, houses, and commercial or office properties.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
meta-feedback
A feedback reporter that collects bug reports and feature requests, then formats them as GitHub Issues. GitHub Issues are shared records used by development teams to track work and problems.