AI Toolbox is a cross-platform desktop application for managing the configuration, providers, models, prompts, plugins, sessions, MCP servers, and skills used by several AI coding assistants. Developers use it to switch and synchronize tools such as OpenCode, Claude Code, Codex, Gemini CLI, OpenClaw, and Pi across local, WSL, and remote SSH environments.
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.
npx agentmods add skills/coulsontl/ai-toolbox/release-notesnpx skills add coulsontl/ai-toolbox --skill release-notesgit clone --depth 1 https://github.com/coulsontl/ai-toolboxWrote 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/coulsontl/ai-toolbox/release-notes)<a href="https://agentmods.dev/skills/coulsontl/ai-toolbox/release-notes"><img src="https://agentmods.dev/badge/skills/coulsontl/ai-toolbox/release-notes.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 | $0.00080 | $0.04176 |
| Opus 5 | $0.00040 | $0.02088 |
| Sonnet 5 | $0.00016 | $0.00835 |
| Haiku 4.5 | $0.00008 | $0.00418 |
Grade A, and why
release-notes 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Notes
Draft release notes from repository evidence, not guesswork.
This skill is for producing publishable release copy for the next release draft. It is not limited to already published history. Start from the latest relevant tag or release boundary, then include committed and clearly related unreleased candidate changes when the user is drafting the upcoming release before publishing.
Default target
Unless the user says otherwise, assume the target output is a GitHub Release body draft for the next release in this structure:
## What's Changed- A flat bullet list of user-facing changes
- The repository-specific Mac install notice at the end
Copy-friendly final output (required): Always present the full publishable GitHub Release body (from ## What's Changed through the Mac install notice, including the database upgrade notice when applicable) inside a single fenced markdown code block, so the user can copy-paste it in one step. Put any research context, range notes, or caveats outside that code block (above or below it). Do not leave the What's Changed body as plain markdown only.
Do not silently switch the task to updater notes or in-app update copy. If the repository has multiple release surfaces, identify which one the user wants before drafting. If unspecified, produce the GitHub Release body draft first and mention that updater notes may need a shorter variant.
In this repository, default to Chinese release copy unless the user explicitly asks for English or another language.
Evidence order
Always work in this order:
- Determine the release range.
- Read the commit and diff summary for that range.
- Check for clearly related staged or unstaged candidate changes that belong to the same upcoming release.
- Check whether the range or candidate changes include a SQLite database schema upgrade.
- Read merged PRs and candidate PR context when available.
- Read related issues for confirmation and issue references.
- Draft bullets from user-visible impact, not implementation detail.
- Run a final issue-matching pass for every bullet before returning the publishable draft.
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 · 304 lines · 80 tokens per session scan A 1ff08ede046a
release-notes is a skill published in the GitHub repository coulsontl/ai-toolbox (1,333 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 4,176 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
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.
release
Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.
changelog
Create changelog files for important commits in a PR.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
refresh-arm-sdk-release
WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…