ai-tc AGENTS.md

ai-tc AGENTS.md is an instructions file for Codex, OpenCode from akasecurity/ai-tc. It costs 213 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for the ai-tc project. They direct the coding agent to read CLAUDE.md, which contains the project’s enforced development rules.

In plain words
What is it for?
Following the ai-tc project’s coding and contribution conventions before making changes.
Why use it?
They prevent work that would fail the project’s automated checks, such as its no-network, dependency, database, and plugin-hook rules.

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

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.

agentmods badge for ai-tc AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/akasecurity/ai-tc/agents-md.svg)](https://agentmods.dev/instructions/akasecurity/ai-tc/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/akasecurity/ai-tc/agents-md"><img src="https://agentmods.dev/badge/instructions/akasecurity/ai-tc/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 213 This file is loaded in full into every session.
When invoked 213 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 5.1 $0.00213 $0.00213
Opus 5 $0.00106 $0.00106
Sonnet 5 $0.00043 $0.00043
Haiku 4.5 $0.00021 $0.00021

Measured 5d ago against content hash 60faa8913f64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ai-tc 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 5d 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 · 16 lines

What it actually says

AGENTS.md — ai-tc

The conventions live in CLAUDE.md. Read that first, every session.

This repo inverts the usual layout. Elsewhere in the org AGENTS.md carries the substance and CLAUDE.md/GEMINI.md point at it; here CLAUDE.md is canonical, because it is referenced by name from ESLint rule messages, test assertions, and CONTRIBUTING.md — including section citations like "CLAUDE.md §4". Renaming it would break those references, so it stays put and this file points at it.

CLAUDE.md is not optional background: the conventions in it are enforced by ESLint and CI, so code that violates them fails to merge. In particular the no-network rule, the package-dependency and Drizzle walls, and the fail-open requirement for plugin hooks are all machine-checked.

@./CLAUDE.md

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. 5d ago First seen · 16 lines · 213 tokens per session scan A 60faa8913f64

Subscribe to this mod's changes

ai-tc AGENTS.md is an instructions file published in the GitHub repository akasecurity/ai-tc (11 stars, last pushed today), licensed Apache-2.0. It adds 213 tokens to every session, about $0.0011 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.