What is From-LLMs-to-Secure-Agents AGENTS.md?

Repository instructions for From-LLMs-to-Secure-Agents, a project making a source-based visual guide to agentic AI and its security. They define the run process, document map, writing rules, evidence requirements, and project safeguards.

Use them when authoring or reviewing guide chapters, examples, visuals, sources, site changes, or maintenance tasks in that repository.

They keep contributions consistent with the project’s research, writing, visual, and maintenance policies. They also limit work to the correct unit and prevent unsupported or placeholder content.

How RenatoMignone/From-LLMs-to-Secure-Agents configures Codex and Open

Reuse

Borrowing it

Nothing to install: this file belongs to RenatoMignone/From-LLMs-to-Secure-Agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/RenatoMignone/From-LLMs-to-Secure-Agents/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/RenatoMignone/From-LLMs-to-Secure-Agents

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/renatomignone/from-llms-to-secure-agents/agents-md.svg)](https://agentmods.dev/instructions/renatomignone/from-llms-to-secure-agents/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/renatomignone/from-llms-to-secure-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/renatomignone/from-llms-to-secure-agents/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 503 This file is loaded in full into every session.

When invoked 503 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00503	$0.00503
Opus 5	$0.00251	$0.00251
Sonnet 5	$0.00101	$0.00101
Haiku 4.5	$0.00050	$0.00050

Measured 2d ago against content hash a0e3428b2aa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

From-LLMs-to-Secure-Agents 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 · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Build a sequential, source-grounded, visual guide to agentic AI and its security.

Run contract

Run python3 scripts/main.py state resolve. Do not read full PROJECT_STATUS.md or ROADMAP.md during normal runs.
Read returned local AGENTS.md, chapter-plan.md, and only selected policies.
Check for any pending tasks below before starting new units.
Follow the matching author, review, or blocked path in docs/autonomous-workflow.md.
Work on one unit. Stop after review, completion, or a recorded blocker.

Policy map

Scope and structure: docs/project-charter.md, docs/information-architecture.md
Prose and chapters: docs/style-guide.md, docs/chapter-template.md
Sources, visuals, and code: docs/evidence-policy.md, docs/visuals-policy.md, docs/examples-policy.md
Site and upkeep: docs/site-policy.md, docs/maintenance.md, docs/roadmap.md

Invariants

Use simple English; define technical terms on first use. Omit empty placeholders.
Never create ASCII/text-based schemas or scripted/programmatic drawing schemes. Use the image generation skill for PNG/WebP cartoon illustrations matching assets/images/repo-images/source/prompt.txt.
Use 1 to 3 cartoon visuals when they materially improve comprehension. One strong visual is enough for a focused chapter; reserve multiple visuals for architecture, workflow, state, and threat scenarios that need them.
If image generation quota is temporarily exhausted, save prompts in source/ and record a pending entry in AGENTS.md for the next session to generate.
Include a next-unit navigation button at the end of each chapter.
Teach in dependency order: functional architecture before detailed security.
Map risks to components; ground claims in official sources (sources/<chapter-path>/<source-id>.yml).
Keep visuals local and traceable; save visual prompts in source/ before generating. No SVGs.
Keep Markdown canonical; validate the site (npm --prefix site run build && npm --prefix site run check).
Store small runnable examples under examples/<chapter-path>/.
Make minimal implementation code blocks expandable by default using <details><summary>Expand minimal Python implementation</summary>...</details>.
Do not use em dashes.

Read the full file on GitHub · 34 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.

2d ago Changed · +25 tokens per session a0e3428b2aa9
7d ago First seen · 34 lines · 478 tokens per session scan A df52890cdd8d

Subscribe to this mod's changes

From-LLMs-to-Secure-Agents AGENTS.md is an instructions file published in the GitHub repository RenatoMignone/From-LLMs-to-Secure-Agents (6 stars, last pushed 3d ago), licensed MIT. It adds 503 tokens to every session, about $0.0025 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.

Building agents Security agent-security agentic-ai ai-agents ai-security cybersecurity educational-resource

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

From-LLMs-to-Secure-Agents: Instructions file for Codex