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.
npx agentmods add instructions/arch3rpro/ark-space/claude-mdgit clone --depth 1 https://github.com/arch3rPro/ark-spaceWrote 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.
[](https://agentmods.dev/instructions/arch3rpro/ark-space/claude-md)<a href="https://agentmods.dev/instructions/arch3rpro/ark-space/claude-md"><img src="https://agentmods.dev/badge/instructions/arch3rpro/ark-space/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00493 | $0.00493 |
| Opus 5 | $0.00246 | $0.00246 |
| Sonnet 5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
ark-space CLAUDE.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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Guidance
ArkSpace packages reusable agent skills, roles, registries, and plugin metadata for Claude Code and Codex.
Start Here
- Default to the
orchestratorskill/role for lightweight routing. - Use
skill-managerfor creating, adapting, validating, or assigning skills. - Read
AGENTS.mdfor cross-agent project rules; this file adds Claude Code-specific orientation.
Repository Rules
- Keep skills in
skills/<skill-name>/SKILL.md. - Keep callable agent role sources in
agents/. - Keep workflow protocols in
workflows/. - Keep generated host-native agent outputs in
integrations/. - Keep legacy role metadata in
roles/during migration. - Keep source, role, and skill governance in
registry/. - Keep Claude plugin metadata in
.claude-plugin/. - Keep Codex plugin metadata in
.codex-plugin/. - Do not duplicate skill bodies per platform.
Validation
After changing package structure, skills, roles, registries, manifests, README, or agent guidance, run:
python3 scripts/validate-skills.py
For structural changes, run:
python3 scripts/arkspace.py doctor
After changing plugin JSON, run:
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
Release Boundary
Do not publish plugins, push branches, create tags, run release workflows, or change versions unless the user explicitly asks for release/version work.
Private Overlay Boundary
Do not commit:
overlays/personal.yamloverlays/private-skills.yamldocs/superpowers/
Commit only overlay examples and documentation.
Claude Code Notes
.claude-plugin/plugin.jsondescribes this package for Claude Code..claude-plugin/marketplace.jsondescribes local marketplace packaging.- Claude Code should consume the shared
skills/tree rather than a separate.claude/skillscopy. - Callable Claude Code agent files are generated from
agents/intointegrations/claude-code/agents/. - Do not edit generated integrations by hand; update
agents/and regenerate.
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.
- 4d ago First seen · 66 lines · 493 tokens per session scan A f570ef1c3175
ark-space CLAUDE.md is an instructions file published in the GitHub repository arch3rPro/ark-space (2 stars, last pushed 9d ago), licensed MIT. It adds 493 tokens to every session, about $0.0025 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.
Other instructions, from other repositories
openehr-assistant-plugin AGENTS.md
Instructions for Cadasto/openehr-assistant-plugin, covering ai guidelines: openehr assistant plugin, project overview, domain context, companion mcp server and calling conventions the server enforces.
erpaval CLAUDE.md
Instructions for theagenticguy/erpaval, covering erpaval-plugin, repo structure, version management, tools and hooks.
hplan CLAUDE.md
Instructions for kimsanguine/hplan, covering claude.md — hplan project rules (adk l1: memory), hplan context, 9 behavioral rules, rule 1 — think before coding and rule 2 — simplicity first.
vibe-engineering AGENTS.md
Instructions for ash1794/vibe-engineering, covering vibe-engineering, skills, invocation, tool mapping and project conventions.
ed3d-plugins CLAUDE.md
Claude Code instructions for ed3dai/ed3d-plugins, covering ed3d-plugins, conventions, task invocations use xml syntax and version updates require marketplace and changelog sync.
alluvium CLAUDE.md
Claude Code instructions for Tespera/alluvium, covering alluvium · 项目宪法, 一句话, 卖点（readme slogan）, 知识组织模型（核心，详见 docs/knowledgemodel.md） and hook 架构（4 个，详见 docs/hooks.md）.