aquiles-skill AGENTS.md

aquiles-skill AGENTS.md is an instructions file for Codex, OpenCode from luizvb/aquiles-skill. It costs 602 tokens per session, scanned A, original, MIT.

Repository instructions for developing and maintaining the Aquiles reusable agent skill. They explain where source material, references, generated files, scripts, and release files belong.

In plain words
What is it for?
Use them when editing, validating, installing, or releasing the Aquiles skill.
Why use it?
They keep changes organised and make skill behaviour and verification repeatable.

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/luizvb/aquiles-skill/agents-md
Clone the repo
git clone --depth 1 https://github.com/luizvb/aquiles-skill

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 aquiles-skill AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/luizvb/aquiles-skill/agents-md.svg)](https://agentmods.dev/instructions/luizvb/aquiles-skill/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/luizvb/aquiles-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/luizvb/aquiles-skill/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 602 This file is loaded in full into every session.
When invoked 602 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 $0.00602 $0.00602
Opus 5 $0.00301 $0.00301
Sonnet 5 $0.00120 $0.00120
Haiku 4.5 $0.00060 $0.00060

Measured 3d ago against content hash 4b84eceb36eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aquiles-skill 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Aquiles Skill repository guidance

This repository packages a reusable agent skill. Keep this file small, durable, and repository-specific; put detailed workflow knowledge inside skills/aquiles/references/ and enforce repeatable checks in scripts/CI.

Source routing

Concern Source of truth
Skill activation and lifecycle skills/aquiles/SKILL.md
Phase / specialist detail skills/aquiles/references/*.md
2026 artifact requirements and sources skills/aquiles/references/artifact-standards.md
Generated product files skills/aquiles/assets/
Deterministic behavior skills/aquiles/scripts/ and scripts/validate.py
Installation install.sh
Public repository contract root README/community files and .github/

Editing rules

  • Preserve progressive disclosure: keep SKILL.md focused and link optional detail directly.
  • Keep only name and description in SKILL.md frontmatter.
  • Write imperative workflow steps with explicit inputs, outputs, owner, evidence, and gate.
  • Put reusable generated content in assets/; put repeated deterministic operations in scripts/.
  • Treat template headings, stable IDs, CLI flags, safe defaults, and overwrite behavior as compatibility surfaces.
  • Update artifact-standards.md when a material artifact contract changes; cite primary, maintained sources and record review date.
  • Do not make generated products inherit this repository's MIT license; licensing remains explicit opt-in.
  • Keep technical access distinct from mutation authorization for Git, GitHub, Vercel, domains, environment variables, billing, and destructive actions.
  • Never add live secrets, .env values, cookies, customer data, or private repository contents.

Required verification

Run before commit:

python3 scripts/validate.py

Also perform the change-specific check:

  • installer change: fresh isolated install from a clean clone;
  • template or bootstrap change: generate a disposable product and inspect every artifact;
  • workflow or safety change: forward-test representative prompts without remote mutation;
  • release-gate change: test allow, deny, missing-access, and mismatched-target cases;
  • documentation link change: verify links where network access is available.

Read the full file on GitHub · 55 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 · 55 lines · 602 tokens per session scan A 4b84eceb36eb

Subscribe to this mod's changes

aquiles-skill AGENTS.md is an instructions file published in the GitHub repository luizvb/aquiles-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 602 tokens to every session, about $0.0030 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.