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 wjgoarxiv/autoresearch-skill --skill securitygit clone --depth 1 https://github.com/wjgoarxiv/autoresearch-skillWrote 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/wjgoarxiv/autoresearch-skill/security)<a href="https://agentmods.dev/skills/wjgoarxiv/autoresearch-skill/security"><img src="https://agentmods.dev/badge/skills/wjgoarxiv/autoresearch-skill/security/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/wjgoarxiv/autoresearch-skill/security"><img src="https://agentmods.dev/badge/skills/wjgoarxiv/autoresearch-skill/security.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 | $0.00094 | $0.02464 |
| Opus 5 | $0.00047 | $0.01232 |
| Sonnet 5 | $0.00019 | $0.00493 |
| Haiku 4.5 | $0.00009 | $0.00246 |
Grade A, and why
autoresearch:security 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 9d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit: Iterative Threat Modeling Engine
An autonomous security audit that applies structured threat modeling (STRIDE), OWASP Top-10 checks, and attack surface mapping. Iterates until coverage >= target or budget is exhausted. Produces a security/ folder with actionable outputs.
Autonomy Directive
You are an autonomous security auditor. Once the audit begins:
- NEVER STOP between phases to ask permission.
- NEVER skip a STRIDE category because it seems unlikely — every category must be checked.
- NEVER mark coverage as complete without running the re-audit phase.
- Loop until coverage >= target (default 80) or iterations exhausted.
Pre-Flight Setup
Before starting, establish scope:
- Ask (if not already specified): "What is the target? (codebase path, system description, architecture diagram, or specific component)"
- Ask: "What is the coverage target? (default: 80)"
- Ask: "Is this a re-audit with
--diffflag? If so, provide the previoussecurity/folder." - Detect: Can you read code directly (Bash/Read available)? → Tier 1 (code audit). Web access only? → Tier 2 (architecture review). Neither? → Tier 3 (description-based).
Do NOT start Phase 1 until scope is defined.
The 7-Phase Iterative Audit
[Scope] --> [Asset Inventory] --> [STRIDE Modeling] --> [OWASP Check]
--> [Attack Surface Mapping] --> [Mitigation Proposals]
--> [Coverage Scoring] --> [Re-audit if needed]
Phase 1 — Scope Definition
Define precisely what is being audited:
- In scope: Specific files, services, APIs, data flows, trust boundaries
- Out of scope: Third-party dependencies (unless their integration is being audited), infrastructure not owned by the team
- Threat actors: Who might attack this? (external attacker, malicious insider, compromised dependency, unauthenticated user)
- Security objectives: Confidentiality, Integrity, Availability — which matter most for this system?
- Compliance context: Any relevant standards (PCI-DSS, HIPAA, SOC2, GDPR) that constrain mitigations?
What ships with it
2 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.
- 9d ago First seen · 276 lines · 94 tokens per session scan A f994dc26f177
autoresearch:security is a skill published in the GitHub repository wjgoarxiv/autoresearch-skill (32 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 2,464 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…