dot-release

dot-release is a skill for Claude Code, Codex from fmind/dot. It costs 41 tokens per session (594 once invoked), scanned A, original, MIT.

A release procedure for the dot repository, which is a collection of command-line tools and configuration files. It turns Git commit history into a versioned release with a changelog, tag, and publication trigger.

In plain words
What is it for?
Use it to check release prerequisites, calculate the next semantic version, run the repository checks, publish the release tag, and verify publication.
Why use it?
It coordinates versioning, checks, commits, tags, and pushes so a release is not cut from an unverified or outdated branch.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/fmind/dot/dot-release
Any agent
npx skills add fmind/dot --skill dot-release
Clone the repo
git clone --depth 1 https://github.com/fmind/dot

Made for: Claude Code, Codex.

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 dot-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmind/dot/dot-release.svg)](https://agentmods.dev/skills/fmind/dot/dot-release)
Your own site
<a href="https://agentmods.dev/skills/fmind/dot/dot-release"><img src="https://agentmods.dev/badge/skills/fmind/dot/dot-release.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 594 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00041 $0.00594
Opus 5 $0.00020 $0.00297
Sonnet 5 $0.00008 $0.00119
Haiku 4.5 $0.00004 $0.00059

Measured yesterday against content hash 6fc8a6ad12f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dot-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 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.

.agents/skills/dot-release/SKILL.md · 43 lines

What it actually says

Dot Release

dot release (alias dot r, wrapped as mise run release) turns the Conventional Commits since the last tag into a release commit and tag of this repository; the generic process and the post-publication verification live in release.

Commands

mise run release -- -y   # non-interactive: skips the confirmation prompt
dot release              # interactive: confirms before mutating

Workflow

The command performs every step itself; the agent checks the preconditions and reads the result.

  1. Preconditions: clean working tree on main, gh authenticated, git-cliff and mise installed, Conventional Commits history.
  2. Fetch and prove: the command fetches origin and requires HEAD == origin/main before any mutation.
  3. Compute and write: the next semver from git-cliff, then dot/version.go and CHANGELOG.md.
  4. Gate: the local gate (format, check, test) runs; a failure aborts and resets the staged release files before any commit or tag exists.
  5. Commit, tag, push: the release commit, the annotated tag, the push of main and refs/tags/v* to origin, then the updated local dot binary is reapplied.
  6. Publish: the tag push triggers .github/workflows/cd.yml, which creates the GitHub release; verify it with the release skill's Verify steps.

Gotchas

  • No mr: the fish abbreviation is interactive-only; agents call mise run release or dot release.
  • Diverged main: the command refuses a dirty tree or a HEAD that differs from origin/main; commit or stash, then sync before retrying.

Documentation

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. yesterday First seen · 43 lines · 41 tokens per session scan A 6fc8a6ad12f4

Subscribe to this mod's changes

dot-release is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 594 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 2026-09-03.