aptl AGENTS.md

aptl AGENTS.md is an instructions file for Codex, OpenCode from Brad-Edwards/aptl. It costs 1,309 tokens per session, scanned A, original, MIT.

Repository-specific instructions for APTL, the Advanced Purple Team Lab, covering its requirements workflow, testing, code checks, and agent setup.

In plain words
What is it for?
They are for reading the repository's Ground Control configuration, running pytest and pre-commit checks, following planning rules, and installing the project's shared agent skills.
Why use it?
They give an agent the project context and completion rules needed to work consistently in that repository.

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/brad-edwards/aptl/agents-md
Clone the repo
git clone --depth 1 https://github.com/Brad-Edwards/aptl

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 aptl AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/brad-edwards/aptl/agents-md.svg)](https://agentmods.dev/instructions/brad-edwards/aptl/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/brad-edwards/aptl/agents-md"><img src="https://agentmods.dev/badge/instructions/brad-edwards/aptl/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,309 This file is loaded in full into every session.
When invoked 1,309 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 $0.01309 $0.01309
Opus 5 $0.00655 $0.00655
Sonnet 5 $0.00262 $0.00262
Haiku 4.5 $0.00131 $0.00131

Measured 3d ago against content hash f5874eea732b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aptl 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 3d 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 · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

This repository (APTL — Advanced Purple Team Lab) uses Ground Control for requirements management and workflow automation.

Ground Control Context

This repo's Ground Control project id, workflow commands, SonarCloud settings, and plan rules live in .ground-control.yaml at repo root (with larger rule files under .gc/). Agents read it via the gc_get_repo_ground_control_context MCP tool, which returns the full workflow config in a single call.

Key facts encoded there today:

  • Ground Control project: aptl
  • GitHub repo: Brad-Edwards/aptl
  • Test / completion command: pytest
  • Lint / format command: pre-commit run --all-files
  • SonarCloud project key: Brad-Edwards_aptl (org: brad-edwards)
  • Plan rules: .gc/plan-rules.md

Skill Installation

The canonical agent-neutral implement and review-tests skills are maintained in the Ground Control repo at skills/implement/SKILL.md and skills/review-tests/SKILL.md. They are installed at the user level — not committed per-repo — by running, from a Ground Control checkout:

bin/install-skills.sh

That script symlinks the canonical skills into:

  • ~/.claude/skills/ (Claude Code)
  • ~/.codex/prompts/ (Codex)

Both Claude and Codex therefore read the same source-of-truth SKILL.md. Re-run the script after pulling Ground Control to refresh. Use --copy on hosts without symlink support and --no-codex if Codex isn't installed locally.

This repo intentionally does not ship .claude/skills/implement/ or .claude/skills/review-tests/ — those were per-repo duplicates superseded by Ground Control PR #792. Other repo-local skills under .claude/skills/ (e.g. ship, stage, gh-workflow-monitor, wave-issue-coverage) remain in place because they are aptl-specific or not yet promoted to the agent-neutral set.

ACES Asset Inventory Capture Skill

The asset inventory capture methodology and reusable capture tooling are maintained in the ACES repo. Agents working APTL inventory issues should install the ACES skill at the user level from an ACES checkout:

Read the full file on GitHub · 130 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. 3d ago First seen · 130 lines · 1,309 tokens per session scan A f5874eea732b

Subscribe to this mod's changes

aptl AGENTS.md is an instructions file published in the GitHub repository Brad-Edwards/aptl (23 stars, last pushed 10d ago), licensed MIT. It adds 1,309 tokens to every session, about $0.0065 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 2026-08-30.