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 mappedsky/seizu --skill cve-repo-assessmentgit clone --depth 1 https://github.com/mappedsky/seizuWrote 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/mappedsky/seizu/cve-repo-assessment)<a href="https://agentmods.dev/skills/mappedsky/seizu/cve-repo-assessment"><img src="https://agentmods.dev/badge/skills/mappedsky/seizu/cve-repo-assessment/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/mappedsky/seizu/cve-repo-assessment"><img src="https://agentmods.dev/badge/skills/mappedsky/seizu/cve-repo-assessment.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 | $0.00027 | $0.00730 |
| Opus 5 | $0.00014 | $0.00365 |
| Sonnet 5 | $0.00005 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
cve-repo-assessment 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 yesterday.
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.
What it actually says
Newly discovered CVEs may affect the repository the repo input names. Evaluate each CVE and maintain the repository's findings report. Work from the provided data and tool evidence only.
Inputs — the values arrive in the ## Inputs block below these instructions:
repo— the repository fullname to assess.cves— a JSON array of {repo, cve_id, severity, score, description, package, patched_version, url, created_at}.
Workflow:
- For each distinct
cve_idincves, callcve_analysis__get_cveto confirm severity, score, and description. If a CVE is not found, keep the provided data and note the gap. - Derive the GitHub organization from the
repofullname prefix (the part before/). Callgithub_security__top_vulnerabilitieswith thatorg,repos=therepofullname, andstate='open'to confirm which CVEs map to open security issues, with package, manifest, and patched-version evidence.reposfilters in the query, so every row returned is already this repository's — do not fetch the organization and filter the rows yourself. - Call
reports__listand look for a report named exactlyCVE Findings –followed by therepofullname. - If it does not exist, call
reports__createwith that exact name, then continue with step 5 using the returned report_id. - Call
reports__getfor the latest config when the report already existed. Then callreports__create_versionwith a complete report config:schema_version: 1name:CVE Findings –followed by therepofullnamequeries: an object mapping query names to Cypher strings ({}when none; never a list). Keep any existing entries; no new queries are required.rows: keep existing rows and prepend one new row named with the current date containing a single full-width markdown panel that summarizes: each evaluated CVE (id, severity, score), the affected package and patched version when known, whether an open security issue confirms exposure, and a recommended remediation order.- A markdown panel's content MUST be in its
markdownfield, exactly this shape (noconfigorcontentkeys):{"type": "markdown", "w": 12, "markdown": "## Findings..."} - Pass a
commentdescribing the run (for example "Automated CVE assessment").
- Do not delete or rewrite prior findings — the report is versioned and prior rows must be preserved.
Output format:
- Finish with a concise summary for the repository: evaluated CVE count, confirmed-exposure count, the report name and version you created, and the top remediation action.
- Keep every claim evidence-backed; state explicitly when a CVE has no matching open security issue in the graph.
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.
- yesterday First seen · 32 lines · 27 tokens per session scan A f2044c5900f6
cve-repo-assessment is a skill published in the GitHub repository mappedsky/seizu (5 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 730 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 2026-09-11.
Other skills, from other repositories
tutti-agent-workspace-app
Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…
assimilate-popular-workflows
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable…
mcp-app-verification
Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.
verification-suite
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.
guardrails-ai-setup
Guardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured output enforcement.
mcp-app-scaffolding
Scaffolds MCP App project structure with correct directory layout, dependencies, entry points, and framework-specific templates. Handles React (useApp hook), Vanilla JS, Vue, Svelte, Preact, and Solid.