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 ashtonian/llm-init --skill security-reviewgit clone --depth 1 https://github.com/ashtonian/llm-initWrote 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/ashtonian/llm-init/security-review)<a href="https://agentmods.dev/skills/ashtonian/llm-init/security-review"><img src="https://agentmods.dev/badge/skills/ashtonian/llm-init/security-review.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.00775 |
| Opus 5 | $0.00006 | $0.00387 |
| Sonnet 5 | $0.00002 | $0.00155 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
security-review 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 7d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perform a security review of the codebase or a specific feature.
Instructions
- Read
.claude/rules/agent-guide.mdfor project context and tech stack. - Read
docs/spec/.llm/PROGRESS.mdfor known security considerations. - Perform a systematic security assessment covering the categories below.
Input Validation & Injection
- All user input is validated at system boundaries (handlers, CLI, config)
- SQL queries use parameterized statements (no string concatenation)
- Command execution inputs are properly escaped
- File paths from user input are sanitized (no path traversal)
- HTML output is escaped to prevent XSS
- JSON/XML parsing has size limits and depth limits
Authentication & Authorization
- Auth checks exist on all protected endpoints
- Token/session handling follows best practices (expiry, rotation, secure storage)
- Password handling uses proper hashing (bcrypt/argon2/scrypt, not MD5/SHA)
- Rate limiting exists on auth endpoints
- Privilege escalation paths are checked
- CORS policy is properly configured
Data Protection
- Sensitive data is not logged (passwords, tokens, PII)
- Secrets are not hardcoded in source (check for API keys, passwords, tokens)
- Environment variables used for secrets, not config files committed to git
- Data at rest encryption where required
- Data in transit uses TLS
- PII handling complies with requirements (GDPR, CCPA, etc.)
Dependencies
- No known vulnerable dependencies (run
go vuln check,npm audit, etc.) - Dependencies are pinned to specific versions
- Minimal dependency surface (no unnecessary packages)
- No dependencies with concerning permissions or behaviors
Error Handling & Information Disclosure
- Error messages don't leak internal details to external users
- Stack traces are not exposed in production responses
- Debug endpoints are disabled in production
- Logging doesn't include sensitive request/response bodies
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.
- 7d ago First seen · 98 lines · 12 tokens per session scan A e2f335d86914
security-review is a skill published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 775 once invoked, about $0.0001 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 2026-08-31.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…