Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MSApps-Mobile/claude-plugins/plugin install sosa-governorWrote 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-governor)<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/sosa-governor"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/sosa-governor/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-governor"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/sosa-governor.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 | $0.00127 | $0.00987 |
| Opus 5.5 | $0.00051 | $0.00395 |
| Sonnet 5.5 | $0.00025 | $0.00197 |
| Haiku 4.5 | $0.00013 | $0.00099 |
Grade A, and why
sosa-governor 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SOSA Governor — On-Demand Audit & Reporting
This skill provides manual governance operations. The hooks handle real-time classification and gating automatically; this skill handles reporting, configuration, and manual overrides.
Audit Report
When the user asks for a SOSA audit or governance report:
- Read the audit log at
${CLAUDE_PLUGIN_ROOT}/audit/for today's date (YYYY-MM-DD.jsonl) - Parse each line as JSON — fields: timestamp, session_id, tool, impact_level, reason, decision
- Summarize:
- Total tool calls today
- Breakdown by impact level (low / medium / high)
- Denied actions (high-impact that were blocked)
- Most active tools
- Sessions with the most activity
- Present as a clear table
Trust Score Management
When the user asks about trust scores or wants to reset trust:
- Read
${CLAUDE_PLUGIN_ROOT}/config/trust-state.json - The
toolsobject maps tool names to trust scores (0.0 = no trust, 1.0+ = auto-approved) - Display current trust scores for all tools that have scores
- To reset a tool's trust: update the JSON, setting the tool's score back to 0
Trust formula:
- Each successful approval: +0.1
- Each incident: -0.5
- Threshold for auto-approval: 1.0 (requires ~10 successful approvals)
Impact Registry
When the user asks which tools are classified at what level:
- Read
${CLAUDE_PLUGIN_ROOT}/config/impact-registry.json - Display the three tiers (high, medium, low) with tools and reasons
- The user can request reclassification — edit the registry JSON accordingly
- Default level for unregistered MCP tools: medium
Token Budget Status
When the user asks about token budgets:
- Read
${CLAUDE_PLUGIN_ROOT}/config/budgets.json - Show the budget hierarchy: monthly → weekly → daily → per-category
- Compare against today's audit log to estimate actual usage
- Flag categories approaching their daily limit (>80%)
Compliance Check
When the user asks to check SOSA compliance:
Evaluate the current setup against SOSA levels:
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 · 113 lines · 127 tokens per session scan A cbefef3ada0f
sosa-governor is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 987 once invoked, about $0.0005 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 2026-09-13.
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.