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/pedroknigge/arkgate/agents-mdgit clone --depth 1 https://github.com/pedroknigge/arkgateWrote 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/pedroknigge/arkgate/agents-md)<a href="https://agentmods.dev/instructions/pedroknigge/arkgate/agents-md"><img src="https://agentmods.dev/badge/instructions/pedroknigge/arkgate/agents-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 | $0.06375 | $0.06375 |
| Opus 5 | $0.03188 | $0.03188 |
| Sonnet 5 | $0.01275 | $0.01275 |
| Haiku 4.5 | $0.00637 | $0.00637 |
Grade A, and why
arkgate 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.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ArkGate Enforcement (self-hosted)
Identity — read this first (every agent)
Git / clone only. This file is not published in the npm package. Consumers who
npm install arkgatenever see it. Do not copy this Identity block into generated consumerAGENTS.md, README, or other surfaces that ship with the library.
This working tree is the mother / canonical development repository for the ArkGate library.
| Fact | Meaning for you |
|---|---|
| What this is | Source of truth for product ArkGate, npm package arkgate, dual CLIs arkgate* + ark*, MCP, published skills (templates/skills/), and the optional runtime kernel. |
| What this is not | A normal app that depends on arkgate. Consumer monorepos (product apps, galleries, client projects) are downstream — never treat this tree as “just another project with arkgate installed.” |
| Where you are | Library authoring root. Edits here ship (or dogfood) the package itself. |
| Contract shape | Self-hosted 4-layer profile in ark.config.json (DomainModel / Kernel / Tooling / FrameworkAdapters) — not the default 11-layer consumer starter. |
| Dogfood | Gates run on this tree via local bin/ + dist/ after npm run build. Prefer workspace CLIs over a stale global arkgate. |
If the task is “improve arkgate the product,” you are in the right place. If the task is “adopt Ark on a business app,” you are usually in a different repository that lists arkgate as a dependency.
Project knowledge map
Code and manifests are the source of truth for implementation details and for whether a structural claim is true. Documentation is organized in three public lanes — use the map, not every historical file:
| Lane | Entry | Audience |
|---|---|---|
| Use | docs/use.md | Anyone shipping with AI |
| Develop | docs/develop.md | Integrate gates, hosts, CI, brownfield |
| Contribute | CONTRIBUTING.md | Improve this library |
| Docs hub | docs/README.md | Full navigation |
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.
- 3d ago First seen · 213 lines · 6,375 tokens per session scan A b98d61ccbba7
arkgate AGENTS.md is an instructions file published in the GitHub repository pedroknigge/arkgate (1 stars, last pushed 3d ago), licensed MIT. It adds 6,375 tokens to every session, about $0.0319 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
coderadius AGENTS.md
Instructions for coderadius-ai/coderadius, covering agents.md, what this is, build & run commands, testing and architecture.
coderadius CLAUDE.md
Instructions for coderadius-ai/coderadius, covering claude.md, what this is, build & run commands, testing and architecture.
fastify-boilerplate AGENTS.md
AGENTS.md instructions for marcoturi/fastify-boilerplate, covering agents.md, project overview, quick reference, architecture and layer boundaries (critical).
traverse AGENTS.md
Instructions for traverse-framework/traverse, covering traverse — agent coordination, agent coordination, 1. check for claude code claim, 2. check for claude code branch and 3. claim the ticket (only if pre-flight passes).
FrameCode-VibeWork AGENTS.md
Instructions for Sistema2D/FrameCode-VibeWork, covering agents.md, instruction order, reading-trigger rule, regression rule and when a plan is required.
symphony AGENTS.md
Instructions for broomva/symphony, covering agents.md - symphony, repository purpose, architecture, key design decisions and gathering context from the knowledge graph.