Neva is a statically typed programming language in which programs are message-passing graphs: nodes exchange data through ports and run concurrently by default. It is for developers building compiled programs with dataflow control, visual editing, and interoperability with Go. The catalogue includes skills and instructions for working with Neva.
Borrowing it
Nothing to install: this file belongs to nevalang/neva. 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/nevalang/neva/main/.codex/skills/release-neva/SKILL.mdgit clone --depth 1 https://github.com/nevalang/nevaWrote 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/nevalang/neva/release-neva)<a href="https://agentmods.dev/skills/nevalang/neva/release-neva"><img src="https://agentmods.dev/badge/skills/nevalang/neva/release-neva.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 5.1 | $0.00040 | $0.00999 |
| Opus 5 | $0.00020 | $0.00500 |
| Sonnet 5 | $0.00008 | $0.00200 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
release-neva 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 5d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neva Release Skill
Overview
Use this skill to prepare a monthly release for nevalang/neva with consistent notes and assets.
Default output is a draft GitHub release, not immediate publication.
Core Tools
gh(release + PR metadata)git(range and branch state)make(artifact build)shasum(asset checksums)- GitHub web UI (optional final review/publish)
Workflow
- Confirm version bump policy before tagging.
- If the bump is ambiguous, ask explicitly:
patchorminor. - Default to
patchfor internal-only changes (CI, docs, lint, infra, refactors without user-facing behavior change). - Use
minorfor user-facing language/stdlib/CLI features or meaningful behavior additions. majoris out of routine flow; always ask.
- If the bump is ambiguous, ask explicitly:
- Sync to clean, up-to-date main state.
git fetch origin --tags --prune- ensure working tree is clean
- ensure build source equals
origin/main(or use a clean worktree from it)
- Read release style from recent history.
- inspect 1-2 previous release notes via
gh release view ... --json body,publishedAt - do not download previous binary assets
- inspect 1-2 previous release notes via
- Collect merged PRs in the release window.
- determine range from previous tag (for example
vX.Y.Z..origin/main) - gather merged PR numbers and read each PR description (
gh pr view)
- determine range from previous tag (for example
- Bump repository version references.
- update
pkg/version.goto the next release version without thevprefix - update checked-in Neva manifests and examples that pin the current language version
(
std/neva.yml,examples/neva.yml,benchmarks/neva.yml,e2e/**/neva.yml, and internal test manifests) - update docs and tests that show or assert the current version
- update generated headers only when they embed the current version string
- run
rg "v?X\\.Y\\.Z"for the previous version and inspect every remaining hit; only leave historical changelog/release-note references intentionally
- update
- Draft release notes.
- keep style concise and factual
- include: theme/title, summary, key sections, related PR list, full changelog compare link
- if changes are mostly internal, say that directly
- include examples for user-facing changes:
- CLI changes: add at least one command snippet showing new command/flag usage
- language changes: add at least one Nevalang code snippet
- keep examples small; full compilable wrappers are optional
- Build assets locally from clean main state.
make build- verify expected platform binaries are present
- compute checksums with
shasum -a 256
- Create draft release with assets.
gh release create <tag> <assets...> --target main --title <tag> --notes-file <file> --draft- verify metadata and uploaded assets via
gh release view <tag> --json ...
- Report back.
- release URL
- included PRs
- asset names and checksums
- note whether release remains draft (default)
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.
- 5d ago First seen · 89 lines · 40 tokens per session scan A 86f9e00b21ca
release-neva is a skill published in the GitHub repository nevalang/neva (1,079 stars, last pushed 14d ago), licensed MIT. It adds 40 tokens to every session and 999 once invoked, about $0.0002 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 2026-09-01.
Other skills, from other repositories
publish-release
Cut and publish a versioned release of @loopdive/js2 + the js2wasm proxy — bump both manifests in lockstep, land a reviewed release PR, then push the vX.Y.Z tag that triggers npm/JSR publish. Use this whenever the user wants to release, publish, ship, cut, or tag a version, bump the version number, push a release tag…
conventional-git
Conventional Commits v1.0.0 branch naming and commit message standards for GitHub and GitLab projects. Use when creating branches, writing commits, generating commit messages, reviewing branch conventions, or setting up changelog automation. Apply when your project needs consistent git history, SemVer-driven releases…
octocat
Handles git and GitHub operations using the gh CLI. Use when the user asks about pull requests (PRs), GitHub issues, repo management, branching, merging, rebasing, cherry-picking, merge conflict resolution, commit history cleanup, pre-commit hook debugging, GitHub Actions workflows, or releases. Covers creating and…
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.