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 skills/ondeinference/onde-cli/distributionnpx skills add ondeinference/onde-cli --skill distributiongit clone --depth 1 https://github.com/ondeinference/onde-cliWhat 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 | $0.00055 | $0.01869 |
| Opus 5 | $0.00028 | $0.00934 |
| Sonnet 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 yesterday.
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.
- yesterday First seen · 263 lines · 55 tokens per session scan A 3bc150907872
distribution is a skill published in the GitHub repository ondeinference/onde-cli (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,869 once invoked, about $0.0003 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 skills, from other repositories
claude-maintain-models
Add new AI models to Kiln's mlmodellist.py and produce a Discord announcement. Use when the user wants to add, integrate, or register a new LLM model (e.g. Claude, GPT, DeepSeek, Gemini, Kimi, Qwen, Grok) into the Kiln model list, mentions adding a model to mlmodellist.py, asks to discover/find new models that are…
kiln-prerelease-check
Run the Kiln pre-release smoke test suite plus the standard CI checks (checks.sh), diagnose every prerelease test that broke (and why), and write a clean readable report with recommended actions. Read-only — it never edits code. Use when the user wants to validate a release candidate, run prerelease tests, or asks for…
release-digest
Post a "what's changed since the last release" recap to the release Slack channel for final QA. Groups merged PRs by author and classifies each as feature / bug fix / task. Use when the user wants a release recap, a changelog since the last tag, or to prep QA before cutting a release from main.
kiln-check-deprecation
Check Kiln's model list for deprecated or sunset models across all providers. Use when the user wants to find deprecated models, check model availability, audit the model list for stale entries, or mentions model deprecation/sunset/end-of-life.
kiln-check-finetune-deprecation
Check Kiln's fine-tunable model list for deprecated or unsupported base models. Use when the user wants to audit fine-tuning support, check if fine-tune base models are still valid, or mentions fine-tune model deprecation.
playwright
Look at Kiln's UI in a real browser, and run its end-to-end tests. Use when checking UI you are changing, taking a screenshot of the app, driving the app with playwright-cli, starting the dev sandbox with playwrightserver.sh, running or debugging npm run tests:e2e, or working with the seeded fixture project that gives…