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 Lu1sDV/skillsmd --skill vuln-researchgit clone --depth 1 https://github.com/Lu1sDV/skillsmdWrote 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/lu1sdv/skillsmd/vuln-research)<a href="https://agentmods.dev/skills/lu1sdv/skillsmd/vuln-research"><img src="https://agentmods.dev/badge/skills/lu1sdv/skillsmd/vuln-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/lu1sdv/skillsmd/vuln-research"><img src="https://agentmods.dev/badge/skills/lu1sdv/skillsmd/vuln-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 | $0.00179 | $0.13213 |
| Opus 5 | $0.00089 | $0.06606 |
| Sonnet 5 | $0.00036 | $0.02643 |
| Haiku 4.5 | $0.00018 | $0.01321 |
Grade A, and why
vuln-research scanned grade A with 1 finding 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 12d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| Node.js sinks | `references/sinks/javascript.md` | JS/Node code audit (child_process, prototype pollution) | The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- commands/vuln-swarm.md 16 KB
- README.md 17 KB
- references/agent-sweep.md 12 KB
- references/audit-poc-report.md 29 KB
- references/auth-access-logic.md 27 KB
- references/automation-platform-attacks.md 22 KB
- references/binary-bug-classes.md 20 KB
- references/binary-code-analysis.md 4.3 KB
- references/binary-exploit-and-specialties.md 17 KB
- references/binary-triage-and-re.md 14 KB
- references/browser-attacks.md 13 KB
- references/chaining-advanced-techniques.md 20 KB
- references/cicd-supply-chain.md 28 KB
- references/client-side-attacks.md 33 KB
- references/dag-reasoning.md 18 KB
- references/freeform-detached.md 4.4 KB
- references/infra-misconfig-attacks.md 15 KB
- references/injection-attacks.md 28 KB
- references/observability-telemetry-attacks.md 24 KB
- references/protocol-infra-attacks.md 43 KB
- references/server-side-attacks.md 38 KB
- references/sink-research-orchestrator.md 5.9 KB
- references/sinks-catalog.md 7.1 KB
- references/sinks/dotnet.md 2.4 KB
- references/sinks/java.citations.jsonl 31 KB
- references/sinks/java.md 30 KB
- references/sinks/java.snippets/CLASS-J001.java 604 B
- references/sinks/java.snippets/CLASS-J002.java 467 B
- references/sinks/java.snippets/CLASS-J003.java 775 B
- references/sinks/java.snippets/CLASS-J004.java 559 B
- references/sinks/java.snippets/CLASS-J005.java 336 B
- references/sinks/java.snippets/CLASS-J006.java 334 B
- references/sinks/java.snippets/CLASS-J007.java 485 B
- references/sinks/java.snippets/CLASS-J008.java 275 B
- references/sinks/java.snippets/CTF-J001.java 404 B
- references/sinks/java.snippets/CTF-J002.java 241 B
- references/sinks/java.snippets/CTF-J005.java 213 B
- references/sinks/java.snippets/CVE-J001.http 150 B
- references/sinks/java.snippets/CVE-J002.xml 121 B
- references/sinks/java.snippets/CVE-J006.java 172 B
- references/sinks/java.snippets/DESER-J001.java 205 B
- references/sinks/java.snippets/DESER-J002.txt 141 B
- references/sinks/java.snippets/DESER-J003.yaml 130 B
- references/sinks/java.snippets/DESER-J004.txt 174 B
- references/sinks/java.snippets/DESER-J005.java 148 B
- references/sinks/java.snippets/DESER-J006.java 160 B
- references/sinks/java.snippets/DESER-J007.java 368 B
- references/sinks/java.snippets/DESER-J008.java 211 B
- references/sinks/java.snippets/DESER-J009.java 304 B
- references/sinks/java.snippets/DESER-J010.java 269 B
- references/sinks/java.snippets/DESER-J011.java 447 B
- references/sinks/java.snippets/FWK-J001.java 214 B
- references/sinks/java.snippets/FWK-J002.java 262 B
- references/sinks/java.snippets/FWK-J003.xml 298 B
- references/sinks/java.snippets/FWK-J004.java 425 B
- references/sinks/java.snippets/FWK-J005.java 185 B
- references/sinks/java.snippets/FWK-J006.java 240 B
- references/sinks/java.snippets/FWK-J007.java 325 B
- references/sinks/java.snippets/FWK-J008.java 230 B
- references/sinks/java.snippets/JVMI-J001.java 269 B
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.
- 12d ago First seen · 614 lines · 179 tokens per session scan A 5ad0afeb7d51
vuln-research is a skill published in the GitHub repository Lu1sDV/skillsmd (2 stars, last pushed today), with no licence file. It adds 179 tokens to every session and 13,213 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
concept-audit
A read-only audit skill for checking code against Daniel Jackson concept models, which describe independent parts of a system and how they work together.
vet
Thorough codebase investigation that finds and fixes real problems. Maps architecture, scans every layer (structural, correctness, security, reliability, performance, hygiene), prioritized report with evidence, fix plan, executes collaboratively. A senior engineer doing a full review with authority to fix. Use when…
debugging
Investigate and safely fix an active, observable software failure, error, regression, or unexpected behavior using reproduction and evidence. Use for the proximate technical cause and remediation. Do not use for a systemic incident postmortem or general performance tuning without a failure.
root-cause-analysis
Produce a systemic, evidence-based incident RCA/postmortem after a failure: timeline, causal chain, contributing conditions, corrective actions, and prevention. Use when recurrence prevention and organizational learning are primary. Do not use as a generic live debugger.
performance-optimization
Measure, diagnose, and improve a performance or capacity objective?latency, throughput, CPU, memory, scalability, or cost?without regressing correctness. Use when performance is the primary requested outcome. Do not use for generic code cleanup or an unmeasured incident postmortem.
code-quality-loop
Iterative review-fix loop: reviews code, auto-fixes issues, repeats until clean or stuck. Finishes with reorganize (for large changes), simplify + test consolidation.