ark-space AGENTS.md

Project instructions for ArkSpace, a workspace for organizing reusable agent skills, roles, and workflows. They define where different source files belong and how changes should be validated and regenerated.

In plain words
What is it for?
Use them when creating or updating skills, agent roles, workflows, registries, integrations, or project configuration in ArkSpace.
Why use it?
They prevent project sources, generated files, platform metadata, and private settings from becoming mixed together. They also provide a consistent workflow for making and checking changes.

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/arch3rpro/ark-space/agents-md
Clone the repo
git clone --depth 1 https://github.com/arch3rPro/ark-space

Made for: Codex, OpenCode.

Per session 661 This file is loaded in full into every session.
When invoked 661 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 $0.00661 $0.00661
Opus 5 $0.00331 $0.00331
Sonnet 5 $0.00132 $0.00132
Haiku 4.5 $0.00066 $0.00066

Measured 2d ago against content hash a486e43524e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ark-space 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guidance

ArkSpace is a creative workspace for orchestrating reusable agent skills, roles, and workflows. Follow these instructions when working in this project.

Project Contract

  • Keep canonical skills in skills/<skill-name>/SKILL.md.
  • Keep callable agent role sources in agents/.
  • Keep orchestration protocols in workflows/.
  • Do not create separate Claude-specific or Codex-specific skill bodies.
  • Use .claude-plugin/ and .codex-plugin/ only for platform metadata.
  • Use roles/ as migration metadata, not as callable runtime behavior.
  • Use registry/ for source governance, role ownership, and skill inventory.
  • Use integrations/ for generated host-native agent outputs.
  • Keep personal or private configuration out of the public package; use ignored files under overlays/.

Default Workflow

  • Use orchestrator for lightweight task routing.
  • Use skill-manager for skill creation, adaptation, registry updates, source tracking, and package validation.
  • Update agents/ when role behavior changes, then regenerate integrations/.
  • Prefer the smallest safe change that satisfies the request.
  • Ask one focused question only when a wrong assumption would materially change the result.
  • For cross-domain or structural changes, design first before editing.

Validation

Run this after changes to skills, roles, registries, plugin manifests, README, docs, or agent guidance:

python3 scripts/validate-skills.py

For structural changes, run the broader doctor command:

python3 scripts/arkspace.py doctor

For plugin manifest edits, also validate JSON:

python3 -m json.tool .claude-plugin/plugin.json >/dev/null
python3 -m json.tool .claude-plugin/marketplace.json >/dev/null
python3 -m json.tool .codex-plugin/plugin.json >/dev/null

Source Governance

Use these modes consistently:

  • mirror: keep close to upstream.
  • adapted: preserve upstream provenance but merge updates selectively.
  • local: maintain directly in this repository.
  • reference-only: record in registry/sources.yaml; do not add to registry/skills.yaml unless promoted into a local skill.

Read the full file on GitHub · 75 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. 2d ago First seen · 75 lines · 661 tokens per session scan A a486e43524e0

Subscribe to this mod's changes

ark-space AGENTS.md is an instructions file published in the GitHub repository arch3rPro/ark-space (2 stars, last pushed 7d ago), licensed MIT. It adds 661 tokens to every session, about $0.0033 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.