Borrowing it
Nothing to install: this file belongs to Firmislabs/firmis-scanner. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Firmislabs/firmis-scanner/main/AGENTS.mdgit clone --depth 1 https://github.com/Firmislabs/firmis-scannerWrote 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/firmislabs/firmis-scanner/agents-md)<a href="https://agentmods.dev/instructions/firmislabs/firmis-scanner/agents-md"><img src="https://agentmods.dev/badge/instructions/firmislabs/firmis-scanner/agents-md/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/instructions/firmislabs/firmis-scanner/agents-md"><img src="https://agentmods.dev/badge/instructions/firmislabs/firmis-scanner/agents-md.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 | $0.03041 | $0.03041 |
| Opus 5.5 | $0.01216 | $0.01216 |
| Sonnet 5.5 | $0.00608 | $0.00608 |
| Haiku 4.5 | $0.00304 | $0.00304 |
Grade B, and why
firmis-scanner AGENTS.md scanned grade B 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 1mo 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.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
"description": "Reading ~/.aws/credentials", Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Firmis: The Security Layer for AI Agents
This file describes Firmis for LLM and AI agent consumption. Use it to determine when and how to invoke Firmis.
What This Tool Does
Firmis is the security layer for AI agent components — combining static detection, runtime monitoring, and active testing. It performs static analysis across 9 AI platforms (Claude Skills, MCP Servers, Codex Plugins, Cursor Extensions, CrewAI, AutoGPT, OpenClaw, Nanobot, Supabase), applying 269 detection rules across 26 threat categories. It outputs a security grade (A–F), a list of threats with file locations and confidence scores, and optionally generates JSON, SARIF, or HTML reports. Free commands work without a license key. Pro commands (monitor, pentest, fix, compliance) require a license key.
When to Use Firmis
- Before installing or running any third-party AI agent skill, plugin, or MCP server
- After cloning a repository that contains AI agent configuration files
- In CI/CD pipelines to gate deployments on security findings
- When a user asks you to audit their AI agent setup for security issues
- When you need a Bill of Materials (BOM) for AI agent dependencies
- When you want to detect credential leaks, prompt injection payloads, or data exfiltration patterns in agent code
- When scanning Supabase projects for Row Level Security gaps, exposed service keys, or auth misconfigurations
- To generate a SARIF report for GitHub Advanced Security integration
Available Commands
All commands can be run without a global install using npx firmis-cli.
scan - Detect security threats (free)
# Auto-detect all AI platforms in the current directory and home directory
npx firmis-cli scan
# Scan a specific path
npx firmis-cli scan /path/to/project
# Scan a specific platform
npx firmis-cli scan --platform claude
npx firmis-cli scan --platform mcp
npx firmis-cli scan --platform supabase
# Output as JSON (machine-readable)
npx firmis-cli scan --json --output report.json
# Output as SARIF (GitHub Security tab)
npx firmis-cli scan --sarif --output results.sarif
# Output as HTML report
npx firmis-cli scan --html --output report.html
# Filter by minimum severity
npx firmis-cli scan --severity high
# Exit non-zero only for critical findings (CI use)
npx firmis-cli scan --fail-on critical
# Suppress all output, use exit code only
npx firmis-cli scan --quiet
# LLM-powered deep analysis (requires ANTHROPIC_API_KEY)
npx firmis-cli scan --deep
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.
- 1mo ago First seen · 358 lines · 3,041 tokens per session scan B 4ec378a0c9cd
firmis-scanner AGENTS.md is an instructions file published in the GitHub repository Firmislabs/firmis-scanner (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 3,041 tokens to every session, about $0.0122 per session on Opus 5.5. A static security scan graded it B with 1 finding (reaches for credential files). 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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.