publish-rust

publish-rust is a skill for Claude Code from Open-Agent-Tools/General-OAT-Skills. It costs 33 tokens per session (2,823 once invoked), scanned A, original, Apache-2.0.

A release workflow for Rust packages, which are reusable libraries or applications published through the Rust package registry. It can handle version changes, checks, commits, tags, pushes, and either CI-based or direct publishing.

In plain words
What is it for?
Use it to release major, minor, hotfix, or release-candidate versions, either by triggering the project's CI pipeline or publishing directly when a registry token is available.
Why use it?
It reduces the manual work and missed steps involved in releasing a Rust package or workspace, a project containing one or more related packages.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the general-oat-skills plugin — 9 skills shipped together

Good fit Use it to release major, minor, hotfix, or release-candidate versions, either by triggering the project's CI pipeline or publishing directly when a registry token is available.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/open-agent-tools/general-oat-skills/publish-rust
Install

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.

Any agent
npx skills add Open-Agent-Tools/General-OAT-Skills --skill publish-rust
Clone the repo
git clone --depth 1 https://github.com/Open-Agent-Tools/General-OAT-Skills

Made for: Claude Code.

Or install general-oat-skills, the plugin that ships this one along with the rest of its 9 skills.

Wrote 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.

agentmods badge for publish-rust

README.md
[![agentmods](https://agentmods.dev/badge/skills/open-agent-tools/general-oat-skills/publish-rust/github.svg)](https://agentmods.dev/skills/open-agent-tools/general-oat-skills/publish-rust)
Your own site
<a href="https://agentmods.dev/skills/open-agent-tools/general-oat-skills/publish-rust"><img src="https://agentmods.dev/badge/skills/open-agent-tools/general-oat-skills/publish-rust/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.

agentmods 80×15 button for publish-rust

Your own site · 80×15
<a href="https://agentmods.dev/skills/open-agent-tools/general-oat-skills/publish-rust"><img src="https://agentmods.dev/badge/skills/open-agent-tools/general-oat-skills/publish-rust.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,823 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.02823
Opus 5 $0.00016 $0.01411
Sonnet 5 $0.00007 $0.00565
Haiku 4.5 $0.00003 $0.00282

Measured 10d ago against content hash acfe09ef4d96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

publish-rust scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Poll `https://crates.io/api/v1/crates/<crate>/versions` (with reqwest/curl) up to 10 times, 10s apart (100s max per crate). Stop polling when the new version appears in the returned list.
skills/publish-rust/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/publish-rust

Generic Rust release skill. Runs a full verification suite locally, bumps the version, commits, creates a signed semver tag, and pushes to trigger the project's release CI. With --local, publishes to crates.io directly instead of relying on CI.

Input

$ARGUMENTS is one of:

  • major — bump first digit (X.0.0)
  • minor — bump middle digit (0.X.0)
  • hotfix — bump last digit (0.0.X)

Optional flags:

  • --rc — tag a pre-release (X.Y.Z-rc.N). Increments N if already on an RC; drops the suffix if --rc is omitted. Pre-releases can be cut from any branch.
  • --local — skip CI path; run cargo publish directly for each crate. Requires CARGO_REGISTRY_TOKEN in the environment.
  • --no-watch — push the tag and exit without streaming the CI workflow (CI-driven mode only).

If $ARGUMENTS is empty or doesn't match major|minor|hotfix, print usage and stop.

Config (optional)

If .claude/publish-rust.toml exists in the project root, read it. Supported keys (all optional):

# Branch required for stable releases (not --rc). Default: "main".
release_branch = "main"

# Tag format. Default: "v{version}".
tag_format = "v{version}"

# Override the default verification gates. If present, these REPLACE the defaults.
# Each entry is a shell command; all must pass. Env vars via "env =".
[[verify]]
name = "fmt"
cmd = "cargo fmt --all -- --check"

[[verify]]
name = "clippy"
cmd = "cargo clippy --workspace --all-features --exclude mycrate-foo -- -D warnings"
env = { RUSTFLAGS = "-D warnings" }

[[verify]]
name = "test"
cmd = "cargo test --workspace --all-features --exclude mycrate-foo"

[[verify]]
name = "doc"
cmd = "cargo doc --workspace --no-deps"
env = { RUSTDOCFLAGS = "-D warnings" }

# --local only: crates to publish, in topological order. Default: auto-detect from
# workspace Cargo.toml, skipping members with publish = false.
[local]
publish_order = ["mycrate-core", "mycrate-adapters", "mycrate-cli"]
inter_publish_sleep_secs = 20

Read the full file on GitHub · 241 lines

Changes

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.

  1. 10d ago First seen · 241 lines · 33 tokens per session scan A acfe09ef4d96

Subscribe to this mod's changes

publish-rust is a skill published in the GitHub repository Open-Agent-Tools/General-OAT-Skills (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 2,823 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.