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/volantlabs/vellis/agents-mdgit clone --depth 1 https://github.com/volantlabs/vellisWrote 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/volantlabs/vellis/agents-md)<a href="https://agentmods.dev/instructions/volantlabs/vellis/agents-md"><img src="https://agentmods.dev/badge/instructions/volantlabs/vellis/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 | $0.04953 | $0.04953 |
| Opus 5 | $0.02476 | $0.02476 |
| Sonnet 5 | $0.00991 | $0.00991 |
| Haiku 4.5 | $0.00495 | $0.00495 |
Grade A, and why
vellis 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 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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository Purpose
Vellis is a library of reusable software components and tooling for AI-native software construction.
The repository should evolve in this order:
- Build a coherent component library.
- Add reference applications that demonstrate how components compose into software solutions.
- Add tooling and SDK surfaces for building software from component models.
- Add runtime support, including distributed-runtime patterns, when the component contracts justify it.
Prefer reusable, self-contained behavior over one-off application code. Treat applications, SDKs, runtimes, and generated systems as consumers of the component library, not as reasons to weaken component boundaries.
Use textual SysML v2 under model/ as the normative source for component and application design. The pinned official Java validator is mandatory through just model-check; repository regex/profile checks are not formal language validation. Validate Foundation, Bibliotek, and Vellis from independently packaged KPAR contents, and keep the official parser-backed inventory and structured conformance objectives current through just model-render. Generated explanatory pages live under generated/reference/, while generated machine projections live under generated/model/. Do not introduce a parallel hand-authored component specification.
Before making or reviewing a SysML/KerML syntax or semantics decision, use
.agents/skills/sysml-reference/SKILL.md and search the generated, checksum-pinned page corpus under
reference/specifications/. Read the smallest sufficient page set, follow normative cross-references,
and state the specification section and page basis for consequential conclusions. Distinguish official
language semantics from informative examples, Vellis modeling conventions, and agent inference. The
official PDFs downloaded by just model-setup remain authoritative; the committed Markdown corpus is
a generated retrieval projection and must not be edited by hand. Validation complements rather than
replaces specification consultation.
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 · 359 lines · 4,953 tokens per session scan A 78014ef90a81
vellis AGENTS.md is an instructions file published in the GitHub repository volantlabs/vellis (8 stars, last pushed 11d ago), licensed Apache-2.0. It adds 4,953 tokens to every session, about $0.0248 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
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
dakera-cli CLAUDE.md
Instructions for Dakera-AI/dakera-cli, covering dakera-cli, key commands, architecture and conventions.
pos CLAUDE.md
Instructions for xcota/pos, covering personal os, rules, memory, budget and hard rules.
pos AGENTS.md
Instructions for xcota/pos, covering agents.md — workspace boot rules, session boot, memory, safety and language.
cli AGENTS.md
Instructions for konteks/cli, covering agent instructions, project overview, tech stack, repository layout and common commands.
context-canopy AGENTS.md
Instructions for YusenZhang0601/context-canopy, covering contextcanopy agent entry, route before acting, privacy and authority boundary, portability claims and completion evidence.