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.
git clone --depth 1 https://github.com/Joncik91/ucaiWrote 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/commands/joncik91/ucai/release)<a href="https://agentmods.dev/commands/joncik91/ucai/release"><img src="https://agentmods.dev/badge/commands/joncik91/ucai/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/commands/joncik91/ucai/release"><img src="https://agentmods.dev/badge/commands/joncik91/ucai/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 | $0.00011 | $0.01435 |
| Opus 5.5 | $0.00004 | $0.00574 |
| Sonnet 5.5 | $0.00002 | $0.00287 |
| Haiku 4.5 | $0.00001 | $0.00144 |
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 1mo 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release
You are helping a developer prepare a release. This command reads git history since the last tag, generates a changelog, bumps the version, and creates a git tag — all with approval gates.
Core Principles
- Git history is the source of truth: Changelog comes from commits, not guesswork
- Cross-reference specs: Connect releases to planned work via requirements.md
- Never push without permission: Create the tag locally, let the user push
- Approval at every step: Changelog, version bump, and tag each need sign-off
- Track progress: Write and update
tasks/todo.mdto track phase completion
Skill Loading — MANDATORY
Before starting, load the DevOps skill.
- Load
Skill(ucai:devops)— releasing is DevOps work
State that you loaded the skill before proceeding.
Phase 1: Analyze
Goal: Understand the current state and determine the release version.
Input: $ARGUMENTS
Actions:
- Create todo list with all phases (1–4)
- Find current version — check in order, use the first found:
package.json→"version"fieldCargo.toml→versionunder[package]pyproject.toml→versionfieldversion.txt- Git tags:
git describe --tags --abbrev=0 - If no version found anywhere, start at
v0.0.0
- Find last tag:
git describe --tags --abbrev=0 2>/dev/null - Get commits since last tag:
git log <last-tag>..HEAD --oneline- If no tags exist, use
git log --oneline
- If no tags exist, use
- Load project context (if available):
- Check
.claude/requirements.md— identify requirements completed since last release (marked[x])
- Check
- Determine version bump:
- If
$ARGUMENTSspecifies a version (e.g.,v2.1.0): use it directly - If
$ARGUMENTSspecifies a bump type (major,minor,patch): apply to current version - If
$ARGUMENTSis empty: analyze commits and suggest:- Breaking changes (commit messages with "breaking", "BREAKING CHANGE", major refactors) → suggest
major - New features ("add", "feat", "implement", "new") → suggest
minor - Bug fixes and maintenance only → suggest
patch
- Breaking changes (commit messages with "breaking", "BREAKING CHANGE", major refactors) → suggest
- Arbitration when commit messages are ambiguous: If no messages explicitly mention breaking changes but the diff shows renamed exports, removed public API methods, changed function signatures, or removed config options — treat as potentially breaking. Present both options: "Commits suggest minor, but I noticed [specific change] which could be breaking. Recommend minor or major?"
- If
- Present summary to user:
- Current version
- Commits since last release (count + key highlights)
- Completed requirements (if requirements.md exists)
- Proposed new version
- Wait for user to confirm or adjust the version
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.
- 1mo ago First seen · 149 lines · 11 tokens per session scan A a867fa2efccf
release is a command published in the GitHub repository Joncik91/ucai (28 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 1,435 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
ia-document-release
Post-ship documentation sync. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, and optionally bumps the version.
ia-changelog
Create engaging changelogs for recent merges to main branch.
version-bump
Bump versions across the monorepo during release process.
release
Bump version, commit, push, mirror to ai-skills, and update local plugin.
release-notes
Assemble release notes / a changelog entry for a commit range, even from non-conventional history.
ship
Branch, commit, open PR, gather Claude + every enabled AI reviewer (Copilot, CodeRabbit, etc.), fix/justify/resolve every finding, loop until clean, then merge. Run only when implementation is finished AND the owner has said to ship (e.g. "ship it") — never self-invoke just because the work looks done. To design and…