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 krzysztofsurdy/code-virtuoso --skill security-researchgit clone --depth 1 https://github.com/krzysztofsurdy/code-virtuosoWrote 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/krzysztofsurdy/code-virtuoso/security-research)<a href="https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/security-research"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/security-research/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/krzysztofsurdy/code-virtuoso/security-research"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/security-research.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 | $0.00076 | $0.02158 |
| Opus 5.5 | $0.00030 | $0.00863 |
| Sonnet 5.5 | $0.00015 | $0.00432 |
| Haiku 4.5 | $0.00008 | $0.00216 |
Grade A, and why
security-research 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security research
Asked to "find a vulnerability", an agent tends to do one of three things: guess at theoretical bugs it never reproduced, skip the vendor's threat model and file a report that gets closed as not applicable, or drift toward tooling that touches systems nobody authorized. This playbook is a gated loop for authorized research. It finds a bug, reproduces it with a minimal proof, classifies it, and reports it through coordinated disclosure.
Hard framing
This comes first and applies to every step. It is not negotiable.
| Rule | What it means |
|---|---|
| Authorization gate | Proceed only for a target the user is authorized to test: an in-scope public bug bounty target, open-source code the user runs in their own isolated lab, or a system the user owns. Never a third-party or production system the user does not own or lacks written authorization for |
| Scope is the authorization | Written scope and rules define what is allowed. Unlisted or out of scope means not authorized. Safe harbor is a promise by the program owner. It is not permission, and it never binds third parties |
| Find, prove, report | The skill finds a bug, reproduces it with a minimal non-weaponized PoC, classifies it, and reports it privately. It does not build weaponized exploits for live third-party systems, help with unauthorized access, mass targeting or evasion, or "confirm impact" on someone else's deployment |
| Lab only for open source | A bug in software other people run is confirmed in your own lab, never on their instances |
| Not legal advice | Legal content here is general information. Check local law: rules outside the US differ and change |
| Stop on doubt | If the target or intent is out of scope, unauthorized, or unclear, stop and tell the user why. Ask for the written scope before doing anything else |
Open by design: the lists are starting points
CVEs, platform rules, tooling and legal posture change within months. Every reference list in this skill is a seed to refresh, never a frozen catalogue. Step 2 below is mandatory on every run, and it repeats whenever a decision depends on something that may have changed.
What ships with it
6 files 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.
- yesterday First seen · 119 lines · 76 tokens per session scan A 2f6429071b17
security-research is a skill published in the GitHub repository krzysztofsurdy/code-virtuoso (36 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 2,158 once invoked, about $0.0003 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 2026-10-23.
Other skills, from other repositories
hermes-diagnostic-review
Use when running a read-only diagnostic review of recent Hermes sessions to find recurring mistakes, failed tool calls, and repeated fixes, then propose suggestion-only improvements and reusable skills. Human-gated; never auto-applies.
instruction-eval
Change one condition an agent runs under (instruction text, the reference material instructions point at, MCP tools and permissions, hooks, skill files), then run the same prompts before and after, several times each, to see what actually changes. Produces an HTML report showing both arms' answers side by side. Use…
worth-building
Decide how elaborate to build something (simple vs. robust) and return a concrete, PoC-shaped proposal at that level — not over- or under-engineered, but right-sized. Use whenever someone is building something and the investment level is unclear: "quick or proper?", "MVP vs. real product", "is this over-engineering?"…
django-ticket-triage
Analyze a Django Trac ticket and produce a triage recommendation report — duplicate search, related PRs, forum threads, and the affected source code. Use when the user gives a Django ticket number, or asks whether a ticket is valid, a duplicate, or ready for a triage stage.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
healthcheck
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).