agentsec AGENTS.md

Project instructions for agentsec, a codebase split into related packages in one repository, known as a monorepo. They define the package manager, folder structure, package names, and how the packages depend on one another.

In plain words
What is it for?
Installing dependencies, running tests and scripts, locating agentsec packages, and understanding the roles and dependency relationships across the repository.
Why use it?
They give coding agents the project context needed to make changes consistently. Following them avoids using the wrong package manager or misunderstanding where a feature belongs.

Instructions file for CodexOpenCode

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/semiotic-ai/agentsec/agents-md
Clone the repo
git clone --depth 1 https://github.com/semiotic-ai/agentsec

Made for: Codex, OpenCode.

Per session 2,609 This file is loaded in full into every session.
When invoked 2,609 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.02609 $0.02609
Opus 5 $0.01305 $0.01305
Sonnet 5 $0.00522 $0.00522
Haiku 4.5 $0.00261 $0.00261

Measured 2d ago against content hash 2ca8848f087d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentsec 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 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.

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.

AGENTS.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Project Rules for Agents

This file provides context and rules for Agents when working in the agentsec monorepo.

Package Manager

Use bun everywhere. Do not use npm, yarn, or pnpm.

  • Install dependencies: bun install
  • Run scripts: bun run <script>
  • Add a dependency: bun add <package>
  • Add a dev dependency: bun add -d <package>
  • Run tests: bun test

Monorepo Structure

This is a Turborepo monorepo with bun workspaces.

agentsec/
  packages/
    shared/        @agentsec/shared       - Shared types and utilities
    scanner/       @agentsec/scanner      - Skill scanner engine
    metrics/       @agentsec/metrics      - Security scoring and metrics
    policy/        @agentsec/policy       - Policy engine and rules
    openclaw/      @agentsec/openclaw     - SKILL.md parser/discovery (platform-agnostic: openclaw, hermes, claude, codex)
    reporter/      @agentsec/reporter     - Report generation
    cli/           @agentsec/cli          - CLI entry point

Although the openclaw/ package is named for the OpenClaw format that originally seeded the SKILL.md spec, it parses and discovers skills across every agentskills.io-conformant platform agentsec supports: OpenClaw / ClawHub, Hermes (Nous Research), Claude Code, and Codex / skills.sh. New agent platforms that emit SKILL.md files only need a path-default entry in packages/shared/src/defaults/ and an inference rule in packages/shared/src/paths/infer-platform.ts.

Package Naming

  • Internal packages: @agentsec/<name>
  • The published CLI package: agentsec

Dependency Graph

shared (types, constants, utilities)
  ^--- scanner  (skill scanning, vulnerability detection)
  ^--- metrics  (security scoring, risk calculation)
  ^--- policy   (policy rules, compliance checks)
  ^--- openclaw (SKILL.md parsing for openclaw/hermes/claude/codex)
  ^--- reporter (HTML/JSON/PDF report generation)

cli (command-line interface, published as "agentsec")
  depends on ALL 6 packages above

Read the full file on GitHub · 184 lines

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 · 184 lines · 2,609 tokens per session scan A 2ca8848f087d

Subscribe to this mod's changes

agentsec AGENTS.md is an instructions file published in the GitHub repository semiotic-ai/agentsec (5 stars, last pushed 2mo ago), licensed MIT. It adds 2,609 tokens to every session, about $0.0130 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.