What is argo AGENTS.md?

A shared instruction guide for coding agents working on Argo, an LLM-based source-code security auditing pipeline. It defines how to identify the target, prepare the environment, respect authorization and spending limits, and run and report audits safely.

Use it as the main operating guide for Argo development or real code audits. It helps agents choose the right procedure and distinguish demonstrations from evidence about user code.

It prevents an agent from changing the auditing tool when the user meant to audit another repository. It also sets boundaries around privacy, scope, commands, and evidence.

How gigioneggiando/argo configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to gigioneggiando/argo. 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/gigioneggiando/argo/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/gigioneggiando/argo

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/gigioneggiando/argo/agents-md/github.svg)](https://agentmods.dev/instructions/gigioneggiando/argo/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/gigioneggiando/argo/agents-md"><img src="https://agentmods.dev/badge/instructions/gigioneggiando/argo/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/gigioneggiando/argo/agents-md"><img src="https://agentmods.dev/badge/instructions/gigioneggiando/argo/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,625 This file is loaded in full into every session.

When invoked 1,625 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	$0.01625	$0.01625
Opus 5.5	$0.00650	$0.00650
Sonnet 5.5	$0.00325	$0.00325
Haiku 4.5	$0.00162	$0.00162

Measured yesterday against content hash 7674c3e1c379, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

argo 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 yesterday.

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 · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Argo: instructions for coding agents

Argo is an LLM-native source-code security-audit pipeline. Most users want you to use Argo to review their code, not to modify Argo. Determine which task they asked for before changing anything. This file is the shared repository entry point; read the agent guide for the relevant procedure, not every doc.

First decisions

Identify the target directory or Git URL, authorized scope, and desired output. Do not assume the Argo checkout itself is the target.
Separate a fixture demonstration from a real audit. Mock output is not evidence about arbitrary user code.
For a real audit, establish the backend, source-sharing constraints, and an approved spend limit before invoking a model. Do not infer these from the agent you are running in; an outer Codex session does not select Argo's Codex backend.
Use the local CLI's --help as the executable command/option contract. Read the corresponding source and tests if the docs disagree. Do not invent commands.

Setup and safe first commands

Run from the Argo checkout with a Python 3.11+ virtual environment. See the installation procedure for POSIX and Windows. Install requirements.txt, then python -m pip install -e . --no-deps in that same environment. The argo console entry point and python -m argo.cli are equivalent. Only the Python dependencies are required for mock; real backends need their own CLI and user-managed authentication. Docker is only needed for optional execution stages.

python -m argo.cli --help
python -m argo.cli screen tests/fixtures/repo --json
python -m argo.cli plan tests/fixtures/repo --objective balanced --json
python -m argo.cli show-routing --runner mock

These discovery commands do not call a model. screen may write a cache outside its target; plan writes a plan under runs/plans/. Neither executes target code. A plan is advisory: inspect it and translate approved choices into actual pipeline flags; it is not automatically applied by a subsequent pipeline command.

Read the full file on GitHub · 116 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.

yesterday First seen · 116 lines · 1,625 tokens per session scan A 7674c3e1c379

Subscribe to this mod's changes

argo AGENTS.md is an instructions file published in the GitHub repository gigioneggiando/argo (66 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,625 tokens to every session, about $0.0065 per session on Opus 5.5. 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 2026-11-05.

Planning Security agentic-ai ai ai-security cybersecurity fault-localization vulnerability detection

argo AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
argo AGENTS.mdgigioneggiando/argo	Instructions file	66	yesterday	Apache-2.0	A	1,625	Codex, OpenCode
AgentHound copilot-instructions.mdadithyan-ak/AgentHound	Instructions file	461	3d ago	Apache-2.0	A	15	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot

argo: Instructions file for Codex