agentmods.dev

drata-cli AGENTS.md

Repository instructions for using the local Drata command-line tool to manage Drata governance, risk, and compliance data and operations.

In plain words
What is it for?
Checking authentication, retrieving company or compliance data, refreshing specifications, previewing changes, and running approved Drata CLI operations.
Why use it?
They standardize commands, authentication checks, read-only reporting, safe write procedures, and handling of API keys.

Instructions file for CodexOpenCode

4 4mo ago A scan 321 tokens original MIT
View the source file ethanolivertroy/drata-cli
Install

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.

agentmods
npx agentmods add instructions/ethanolivertroy/drata-cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/ethanolivertroy/drata-cli

Made for: Codex, OpenCode.

Per session 321 This file is loaded in full into every session.
When invoked 321 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00321 $0.00321
Opus 5 $0.00161 $0.00161
Sonnet 5 $0.00064 $0.00064
Haiku 4.5 $0.00032 $0.00032

Measured 2d ago against content hash 2877c971d0d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

drata-cli 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 2d 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.

- Prefer `drata` over handcrafted `curl` or one-off API scripts.
AGENTS.md · 23 lines

What it actually says

AGENTS.md

Use the local drata CLI for Drata/GRC tasks in this repository.

Detailed workflow: skills/drata-cli-workflow/SKILL.md

Getting oriented

  • CLI entrypoint: src/cli.mjs. Library code: src/lib/. Tests: test/ (run with npm test).
  • OpenAPI specs at specs/v1.json and specs/v2.json are regenerated by npm run refresh-specs. Do not hand-edit.
  • If drata isn't on PATH, run node ./src/cli.mjs instead. Check auth with drata auth status --json before the first API call.
  • Node 20+ required.

Key rules

  • Prefer drata over handcrafted curl or one-off API scripts.
  • Use versionless commands first (e.g. drata get-company --json); only pin v1/v2 when behavior differs or the user asks.
  • Use --json for agent-readable output.
  • Use read-only mode for reporting: DRATA_READ_ONLY=1 or --read-only.
  • For writes, run --dry-run --json first, then execute only after confirming the request shape.
  • Never print, commit, or persist real Drata API keys.
  • Prefer Keychain auth (drata auth login --api-key-stdin), --api-key-file, or DRATA_API_KEY_CMD over inline secrets.
Changes

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.

  1. 2d ago First seen · 23 lines · 321 tokens per session scan A 2877c971d0d1

Subscribe to this mod's changes

drata-cli AGENTS.md is an instructions file published in the GitHub repository ethanolivertroy/drata-cli (4 stars, last pushed 4mo ago), licensed MIT. It adds 321 tokens to every session, about $0.0016 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 2026-08-31.

Legal and complianceagent-skillsapiautomationclicompliancedrata
Related

Other instructions, from other repositories

filegrc AGENTS.md

Instructions for Alignbase/filegrc, covering filegrc repository instructions, purpose, agent-facing product surface, product principles and standards alignment.

Alignbase/filegrc · 4,668 tokens

korean-law-alio-mcp CLAUDE.md

Instructions for scvcoder/korean-law-alio-mcp, covering claude.md, structure, commands, alio 공공기관 내부규정 일괄 수집 (배치) and 보고서형 공시 카테고리 (reportgbn=y) — 단체협약/임금협약/노사협의회.

scvcoder/korean-law-alio-mcp · 3,809 tokens

compliance-agent-skills copilot-instructions.md

Instructions for vaquarkhan/compliance-agent-skills, covering github copilot instructions — compliance-agent-skills, read first, core rules, skill routing (quick) and code changes.

vaquarkhan/compliance-agent-skills · 510 tokens

ai-incident-law CLAUDE.md

Claude Code instructions for snapsynapse/ai-incident-law, covering claude.md — ai incident law, purpose, stack, directory layout and conventions.

snapsynapse/ai-incident-law · 1,031 tokens

privacy-kit-cl AGENTS.md

Instructions for Yugoxc/privacy-kit-cl, covering agents.md — guía de integración para una ia, objetivo, paso 0 — detectar el terreno, paso 1 — instalar y configurar and paso 2 — implementar el store.

Yugoxc/privacy-kit-cl · 869 tokens

mcp-eu-compliance AGENTS.md

AGENTS.md instructions for matematicsolutions/mcp-eu-compliance, covering agents.md - mcp-eu-compliance, project purpose, matematic context (hard constraints), mcp tools (tools contract) and build and test.

matematicsolutions/mcp-eu-compliance · 1,322 tokens