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/release/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/release)<a href="https://agentmods.dev/skills/ondeinference/onde-cli/release"><img src="https://agentmods.dev/badge/skills/ondeinference/onde-cli/release/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/release"><img src="https://agentmods.dev/badge/skills/ondeinference/onde-cli/release.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 | $0.00104 | $0.01662 |
| Opus 5.5 | $0.00042 | $0.00665 |
| Sonnet 5.5 | $0.00021 | $0.00332 |
| Haiku 4.5 | $0.00010 | $0.00166 |
Grade A, and why
release 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 23d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release skill
End-to-end release procedure for onde-cli. Complements the git skill (merge rules)
and the distribution skill (channel details) — this skill is the concrete runbook.
Decide the version
- Look at
git tag -l 'v*' --sort=-v:refname | head -1for the latest release. - Look at the commits since (
git log v<latest>..development --oneline). Fixes and chores only → patch bump. New user-facing features → minor bump. - Check for an abandoned
release/vX.Y.Zbranch — its version is usually the intended next one. If it exists, inspect it (git log development..release/...) before deciding to reuse or delete it; do not blindlybranch -Dwithout looking, and never reuse a branch whose commits were made unsigned or by the wrong identity.
Version bump surfaces
These files pin the crate version and must all move together:
Cargo.toml—version = "X.Y.Z"in[package]pub/onde_cli/pubspec.yaml—version: X.Y.Zserver.json— three occurrences: top-levelversion, and the npm and NuGetpackages[].versionentries (search for the old version string to catch all)
docs/mcp-registry.md and .github/workflows/release-mcp-registry.yml mention
past versions only as historical examples — do not bump those.
The npm wrapper manifests are NOT bump targets: the committed package.json files
are rewritten at release time by npm/scripts/render-*.cjs from the tag.
After editing, run cargo check --locked (or let the build update Cargo.lock)
so the lockfile carries the new version, and commit it in the same bump commit.
Sequence
Follow the git skill's branch flow — release/vX.Y.Z → development → main,
--no-ff at every hop, tag on the final main merge commit. Concretely:
git checkout development
git pull <remote> development # start from the pushed tip
git checkout -b release/vX.Y.Z
# ... edit the bump surfaces ...
git commit -am "Prepare vX.Y.Z" # signed, correct identity (see below)
git checkout development
git merge --no-ff release/vX.Y.Z -m "Merge release prep for vX.Y.Z"
git checkout main
git pull <remote> main
git merge --no-ff development -m "Merge development for vX.Y.Z"
git tag vX.Y.Z
git push <remote> development main vX.Y.Z
git branch -d release/vX.Y.Z # only after the merge lands
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 23d ago First seen · 150 lines · 104 tokens per session scan A 4b412631d316
release is a skill published in the GitHub repository ondeinference/onde-cli (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 104 tokens to every session and 1,662 once invoked, about $0.0004 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 2026-10-14.
release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| releaseondeinference/onde-cli | Skill | 2 | yesterday | Apache-2.0 | A | 104 | Claude Code |
| afk-releasegriffinwork40/agent-afk | Skill | 62 | yesterday | Apache-2.0 | A | 156 | Claude Code |
| aiox-devopsSynkraAI/aiox-core | Skill | 3.1k | yesterday | none | A | 51 | Claude Code |
| aiox-devopsSynkraAI/aiox-core | Skill | 3.1k | yesterday | none | A | 41 | Codex |
| hatch3r-releasehatch3r/hatch3r | Skill | 26 | 1mo ago | MIT | A | 37 | Claude Code |
| ship-prccevans/bobbycode | Skill | 6 | 5d ago | MIT | A | 56 | Claude Code |
| automating-devopstelagod/code-abyss | Skill | 244 | 3mo ago | MIT | A | 76 | Claude Code |