Borrowing it
Nothing to install: this file belongs to ondeinference/onde-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ondeinference/onde-cli/main/.agents/skills/distribution/SKILL.mdgit clone --depth 1 https://github.com/ondeinference/onde-cliWrote 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/skills/ondeinference/onde-cli/distribution)<a href="https://agentmods.dev/skills/ondeinference/onde-cli/distribution"><img src="https://agentmods.dev/badge/skills/ondeinference/onde-cli/distribution/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ondeinference/onde-cli/distribution"><img src="https://agentmods.dev/badge/skills/ondeinference/onde-cli/distribution.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00055 | $0.01869 |
| Opus 5.5 | $0.00022 | $0.00748 |
| Sonnet 5.5 | $0.00011 | $0.00374 |
| Haiku 4.5 | $0.00006 | $0.00187 |
Grade A, and why
distribution 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 2mo 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onde CLI distribution
This skill captures how onde-cli is distributed today and what to watch when adding new channels.
Distribution model
onde-cli is a native Rust CLI first.
Everything else is packaging.
That means:
- build the Rust binary once per target
- publish thin wrappers that install or launch that binary
- keep channel-specific logic small and predictable
This design keeps behavior consistent across ecosystems and avoids re-implementing CLI logic in each language.
Channel map
Native source of truth
- Rust crate:
onde-cli - binary name:
onde - root manifest:
Cargo.toml
Wrapper channels
- npm: JavaScript launcher + optional platform packages
- PyPI:
maturinbinary wheels - NuGet: .NET global tool launcher
- pub.dev: Dart launcher package
Native artifact channels
- crates.io
- GitHub Releases
- Homebrew
Wrapper design patterns
npm
Use a very small Node launcher that:
- detects OS and architecture
- resolves the installed platform package
- spawns the binary with inherited stdio
Good fit for users who already live in npm tooling.
Important release detail:
- the committed
npm/onde-cli/package.jsonis a working file, not the publish-time source of truth - the release workflow rewrites the base package manifest with
npm/scripts/render-main-package.cjs - platform package manifests are generated on the fly with
npm/scripts/render-platform-package.cjs - the actual npm version comes from the release tag via
RELEASE_VERSION, not from manually editing the committed npm manifest before publish
PyPI
Use maturin with bindings = "bin" so the native executable is what gets installed.
Good fit for Python users who want the CLI but not a Python reimplementation.
NuGet
Use a .NET global tool wrapper.
Important details:
- keep the package as a launcher, not a managed rewrite
- place native binaries under the tool payload
- resolve the runtime identifier at startup
- set Unix execute bits before launch
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.
- 2mo ago First seen · 263 lines · 55 tokens per session scan A 3bc150907872
distribution is a skill published in the GitHub repository ondeinference/onde-cli (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 1,869 once invoked, about $0.0002 per session on Opus 5.5. 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.
distribution compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| distributionondeinference/onde-cli | Skill | 2 | yesterday | Apache-2.0 | A | 55 | Claude Code, Codex |
| rea-changelog-updatemorluto/rea | Skill | 435k | yesterday | MIT | A | 33 | Claude Code |
| codew-release-qa-sweepHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 31 | Claude Code, Codex |
| releaseHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 0 | Claude Code, Codex |
| skillshare-changelogrunkids/skillshare | Skill | 2.9k | yesterday | MIT | A | 134 | Claude Code |
| githubAtomicBot-ai/atomic-agent | Skill | 3.4k | 8d ago | MIT | A | 48 | Claude Code, Codex |
| commit-prZaxbyHub/opencode-swarm | Skill | 518 | yesterday | MIT | A | 100 | Codex |