Borrowing it
Nothing to install: this file belongs to irsdl/webhacklist. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/irsdl/webhacklist/master/.claude/skills/webseclist-judge-reference/SKILL.mdgit clone --depth 1 https://github.com/irsdl/webhacklistWrote 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/irsdl/webhacklist/webseclist-judge-reference)<a href="https://agentmods.dev/skills/irsdl/webhacklist/webseclist-judge-reference"><img src="https://agentmods.dev/badge/skills/irsdl/webhacklist/webseclist-judge-reference/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/irsdl/webhacklist/webseclist-judge-reference"><img src="https://agentmods.dev/badge/skills/irsdl/webhacklist/webseclist-judge-reference.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 | $0.00111 | $0.06659 |
| Opus 5.5 | $0.00044 | $0.02664 |
| Sonnet 5.5 | $0.00022 | $0.01332 |
| Haiku 4.5 | $0.00011 | $0.00666 |
Grade A, and why
webseclist-judge-reference 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 15d 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 — 565 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source security
Before handling third-party material, read and follow the shared source-security policy. It governs sandboxed reading/conversion, trusted-policy reviews and validation before any source-derived action. These requirements apply to this entire workflow, including retries, imports and bulk work; no unsafe host fallback is permitted.
Judgy McJudgeFace
Related sources
When researching, adding, updating or reviewing a reference, apply the shared research-story and related-source workflow. Inspect companion papers, series parts, slides, recordings, code, substantive analysis and reproductions. Maintain their relationships and separate credits; keep link-only media accessible. Preserve existing nominations and capture each written source separately. Removing an entry also requires checking its group and shared sources before pruning.
Evaluate web-security research for novelty and lasting value. The skill's
invocation remains /webseclist-judge-reference.
You are deciding one thing: when this candidate first became public, did it add something worth remembering for future web-security work, or was that ground already covered then? Everything below exists to make that judgement evidence-based and consistent, so that two different candidates get compared on the same axis rather than on whichever one had the scarier impact or the more famous author.
The working output is a private structured report; public evaluation records show only Added / Not added. Issue and PR replies follow the submission guidance below. The hard part is not the template — it is doing the prior-art search honestly and separating the underlying idea from the target it happened to hit.
The one bias this skill exists to counter
Impact is not research value. A finding can hand you domain-admin on a Fortune 500 and still teach nothing new (a textbook bug on a big target), while a low-severity quirk in an obscure parser can introduce a primitive that reshapes a whole class of attacks. Reputation, CVE numbers, bounty size, severity, and press coverage are all downstream of things that are not novelty. Score the contribution, not the headline. The neutrality rules below are not decoration; they are the point.
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.
- 15d ago Changed · +25 lines 169ec521bb50
- 20d ago Changed · -2 tokens per session 0b52747912d7
- 1mo ago Changed · +26 lines 851d23fc54f5
- 1mo ago Changed · +13 lines 89aa6d8757d0
- 1mo ago Changed · +50 lines 0268401e0255
- 1mo ago Changed · +46 lines 707f4526bd63
- 1mo ago Changed · +25 lines · -117 tokens per session 8cbe7733a6a3
- 1mo ago First seen · 380 lines · 230 tokens per session scan A 162e75fcbf0c
webseclist-judge-reference is a skill published in the GitHub repository irsdl/webhacklist (907 stars, last pushed 5d ago), licensed MIT. It adds 111 tokens to every session and 6,659 once invoked, about $0.0004 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…