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/dougburks/so-crates/agents-mdgit clone --depth 1 https://github.com/dougburks/so-cratesWrote 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/dougburks/so-crates/agents-md)<a href="https://agentmods.dev/instructions/dougburks/so-crates/agents-md"><img src="https://agentmods.dev/badge/instructions/dougburks/so-crates/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 | $0.08467 | $0.08467 |
| Opus 5 | $0.04234 | $0.04234 |
| Sonnet 5 | $0.01693 | $0.01693 |
| Haiku 4.5 | $0.00847 | $0.00847 |
Grade A, and why
so-crates AGENTS.md 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL "https://unpkg.com/d3@7/dist/d3.min.js" -o static/d3.min.js How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file contains agent-focused guidance for maintaining SO-CRATES.
Updating Vendored Dependencies
SO-CRATES bundles D3 and d3-sankey in static/ so the application works offline and builds remain deterministic.
D3
To update to the latest version:
curl -sL "https://unpkg.com/d3@7/dist/d3.min.js" -o static/d3.min.js
curl -sL "https://unpkg.com/[email protected]/dist/d3-sankey.min.js" -o static/d3-sankey.min.js
After updating, verify the files load correctly and run the test suite:
python3 -m unittest discover -v
If the copyright year changed, update static/LICENSE accordingly.
Check for D3 releases at https://github.com/d3/d3/releases. Recommended cadence: every 6–12 months, or immediately if a security CVE is announced.
Backend Architecture
SO-CRATES's backend is split into domain modules. Do not add new logic directly to socrates.py - place it in the appropriate module:
| Module | Add here if... |
|---|---|
validators.py |
Input validation and the small, focused I/O it depends on (no HTTP framework code). IP/port checks, filename sanitization, URL/SSRF safety (including DNS resolution via resolve_safe_ips and TCP reachability via is_host_reachable), PCAP magic bytes, ZIP slip prevention, file staleness checks. |
suricata_analyzer.py |
Anything related to Suricata lifecycle: config setup, rule downloads, spawning subprocesses, processing locks, file extraction. |
yara_analyzer.py |
YARA scanning: executable checks, rules download/setup, scanning extracted files, parsing output. |
sigma_analyzer.py |
Sigma rule conversion/execution via Zircolite, importing log events into the events DB. Querying sigma_alerts back out is db.py's job, not this module's. |
file_analyzer.py |
Lightweight file metadata extraction (file-command magic/MIME type, Shannon entropy, printable strings). No hashing here - MD5/SHA256 are computed in socrates.py/yara_analyzer.py. |
exif_analyzer.py |
EXIF metadata extraction for image/media files. |
ohmydebn_colors.py |
Deriving a full theme (CSS custom properties) from an OhMyDebn/Aether color palette (colors.toml/alacritty.toml) for the Themes modal's OhMyDebn sync toggle. Pure functions, no I/O. |
playbook_lookup.py |
Security Onion Playbooks lookup - reading the baked-in gzip-compressed indexes (BAKED_IN_PLAYBOOKS_DIR/PLAYBOOKS_DIR), exact-rule/engine-fallback resolution, in-process caching. No fetch/refresh logic - see "Detection Rule Freshness" below for why. |
ai_summary_lookup.py |
AI-generated per-rule summary lookup - same baked-in gzip-compressed-index/in-process-caching shape as playbook_lookup.py (AI_SUMMARIES_DIR), but exact-match only, no engine-wide fallback, and covers nids/sigma/yara (one more type than Playbooks). No fetch/refresh logic - see "Detection Rule Freshness" below. |
db.py |
SQLite schema changes, new query functions, index optimization, bulk loading logic. |
models.py |
New Suricata event field extraction helpers (parsing JSON fields into typed values). |
config.py |
Application-wide constants: size limits, timeouts, thresholds. Adjust here for different deployments. |
socrates.py |
Only HTTP handler methods, request/response formatting, and thin orchestration that calls other modules. |
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.
- 5d ago First seen · 329 lines · 8,467 tokens per session scan A 6867db329dc0
so-crates AGENTS.md is an instructions file published in the GitHub repository dougburks/so-crates (583 stars, last pushed 11d ago), licensed MIT. It adds 8,467 tokens to every session, about $0.0423 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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.
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).