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 agentmods add instructions/stevologic/security-recipes.ai/agents-mdgit clone --depth 1 https://github.com/stevologic/security-recipes.aiWrote 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/instructions/stevologic/security-recipes.ai/agents-md)<a href="https://agentmods.dev/instructions/stevologic/security-recipes.ai/agents-md"><img src="https://agentmods.dev/badge/instructions/stevologic/security-recipes.ai/agents-md.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 | $0.00758 | $0.00758 |
| Opus 5 | $0.00379 | $0.00379 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
security-recipes.ai AGENTS.md 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 3d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Cursor Cloud specific instructions
This repo is an Eleventy static documentation site
(security-recipes.ai) with two optional Python companions. See README.md
("Run the site locally", "Optional MCP server") and CONTRIBUTING.md for the
canonical commands; the notes below only cover non-obvious, durable gotchas.
Services
| Service | What it is | Run command | Port |
|---|---|---|---|
| Eleventy site (primary product) | CVE database + remediation recipe site | npm run serve |
8080 |
| FastMCP server (optional) | Read-only recipe/CVE MCP endpoint at /mcp |
python mcp_server.py |
8000 |
| Remediation suite (optional) | Python CLI for playbook packets | python scripts/security_recipes_remediation_suite.py ... |
n/a |
Non-obvious gotchas
pythonmust resolve to Python 3.10+. The Node build scripts (scripts/check_build_prerequisites.js,package.jsonbuild) invoke the bare commandpython, notpython3. The environment provides this via thepython-is-python3system package plus the deps fromrequirements-dev.txt(which includesrequirements-mcp-server.txt). Ifpythonis missing or lacksfastmcp/httpx/markdown/tomli, the build fails inprebuild.npm run servedoes NOT generate the canonical/cve/<ID>/detail pages. Those pages are materialized bypython scripts/materialize_cve_pages.py, which only runs as part ofnpm run build(noteleventy --serve). To browse CVE detail routes (e.g./cve/CVE-2021-44228/) in the dev server, runnpm run buildonce first to populatepublic/cve/, then startnpm run serve(it keeps the already-materialized files). A fresh checkout served without a prior build will show blank/missing CVE detail pages even though the/cve-database/search page and/api/*.jsonfeeds work.- MCP server source feed.
python mcp_server.pydefaults its recipe index to the publichttps://security-recipes.ai/...URL. To run fully local, build+serve the site, then start it withRECIPES_MCP_SOURCE_INDEX_URL=http://localhost:8080/api/recipes-index.jsonandRECIPES_MCP_ALLOWED_SOURCE_HOSTS=localhost. It speaksstreamable-http; hitPOST /mcpwithAccept: application/json, text/event-stream(a bareGET /mcpreturns 406, which is expected).
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.
- 3d ago First seen · 52 lines · 758 tokens per session scan A 2cfdddd0a0a6
security-recipes.ai AGENTS.md is an instructions file published in the GitHub repository stevologic/security-recipes.ai (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 758 tokens to every session, about $0.0038 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.