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 ersinkoc/security-check --skill sc-verifiergit clone --depth 1 https://github.com/ersinkoc/security-checkWrote 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/ersinkoc/security-check/sc-verifier)<a href="https://agentmods.dev/skills/ersinkoc/security-check/sc-verifier"><img src="https://agentmods.dev/badge/skills/ersinkoc/security-check/sc-verifier/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/ersinkoc/security-check/sc-verifier"><img src="https://agentmods.dev/badge/skills/ersinkoc/security-check/sc-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00014 | $0.02560 |
| Opus 5.5 | $0.00006 | $0.01024 |
| Sonnet 5.5 | $0.00003 | $0.00512 |
| Haiku 4.5 | $0.00001 | $0.00256 |
Grade A, and why
sc-verifier 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SC: Verifier — False Positive Elimination & Confidence Scoring
Purpose
The verifier skill processes all raw candidates from Phase 2, tries to disprove them, merges duplicate root causes, and assigns explicit final verdicts. This is the quality gate that prevents suspicious patterns, missing hardening, and unresolved deployment assumptions from being presented as vulnerabilities.
Apply the evidence contract in sc-orchestrator. When the host supports independent agents, the final verifier must not be the hunter that proposed the candidate. Otherwise use a fresh, separate verification pass and disclose the limitation.
Activation
Runs in Phase 3 of the pipeline, after all Phase 2 vulnerability skills have completed.
Input
- All files matching
security-report/findings/*.json security-report/architecture.mdsecurity-report/coverage-ledger.md
Output
security-report/findings.json— structured final verdictssecurity-report/verified-findings.md— human-readable verification record
Verdict Gate
Every candidate receives exactly one verdict:
confirmed: complete source trace plus safe bounded evidence establish a meaningful trust-boundary failure. Severity is required.needs_validation: a specific runtime, provider, identity, OS, broker, or deployment fact remains decisive. Severity is forbidden; include the exact blocker and safe next check.rejected: reachability, controls, authority, context, or reproduction disproves the claim. Severity is forbidden; include the rejection reason.
Confidence may prioritize review but cannot fill a missing evidence field or promote a lead.
Verification Process
Step 1: Finding Collection
- Read all candidate JSON files from
security-report/findings/ - Parse each finding into a structured format (title, severity, confidence, file, line, type, description)
- Skip files containing "No issues found"
- Create a unified finding list with source skill attribution
- Reject malformed candidates that do not identify an attacker, affected principal/resource, ordered source trace, control analysis, sink, result, and conditions
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 Changed · +51 lines a1d679663c16
- 1mo ago First seen · 228 lines · 14 tokens per session scan A f33e7a9c4260
sc-verifier is a skill published in the GitHub repository ersinkoc/security-check (83 stars, last pushed 17d ago), licensed MIT. It adds 14 tokens to every session and 2,560 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…