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/semiotic-ai/agentsec/agents-mdgit clone --depth 1 https://github.com/semiotic-ai/agentsecWhat 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 | $0.02609 | $0.02609 |
| Opus 5 | $0.01305 | $0.01305 |
| Sonnet 5 | $0.00522 | $0.00522 |
| Haiku 4.5 | $0.00261 | $0.00261 |
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.
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
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.
- 2d ago First seen · 184 lines · 2,609 tokens per session scan A 2ca8848f087d
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.
Other instructions, from other repositories
skillhub AGENTS.md
AGENTS.md instructions for iflytek/skillhub, covering skillhub — agents.md, quick reference, directory map, critical rules and do not manually edit generated files.
ClawTeam-OpenClaw CLAUDE.md
Instructions for win4r/ClawTeam-OpenClaw, covering claude.md, what this project is, common commands, dev install (from repo root) and cli entry points.
coinos-skills CLAUDE.md
Instructions for aicoincom/coinos-skills, covering claude.md, project overview, architecture, coinclaw 三引擎适配 and 关键设计决定.
coinos-skills AGENTS.md
Instructions for aicoincom/coinos-skills, covering coinos skills — agent instructions, 在 coinclaw 三引擎容器里运行, 数据准确性铁则 (严格遵守, 仅次于安全规则), 一、禁止本地计算技术指标 and 二、禁止自己推算合约张数 / 保证金 / 爆仓价.
lalaclaw AGENTS.md
Instructions for aliramw/lalaclaw, covering agents.md, 开发服务启动 / dev servers, 前端开发服务 / frontend, 后端开发服务 / backend and 联调说明 / notes.
last30days-skill-cn CLAUDE.md
Claude Code instructions for Jesseovo/last30days-skill-cn, covering last30days-cn, purpose, structure, commands and release notes.