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 skills add Malo-T/claude-toolbelt --skill slack-changeloggit clone --depth 1 https://github.com/Malo-T/claude-toolbeltWrote 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/malo-t/claude-toolbelt/slack-changelog)<a href="https://agentmods.dev/skills/malo-t/claude-toolbelt/slack-changelog"><img src="https://agentmods.dev/badge/skills/malo-t/claude-toolbelt/slack-changelog/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/skills/malo-t/claude-toolbelt/slack-changelog"><img src="https://agentmods.dev/badge/skills/malo-t/claude-toolbelt/slack-changelog.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 | $0.00332 | $0.02354 |
| Opus 5 | $0.00166 | $0.01177 |
| Sonnet 5 | $0.00066 | $0.00471 |
| Haiku 4.5 | $0.00033 | $0.00235 |
Grade A, and why
slack-changelog 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 12d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slack Changelog
Turn a release into a message the rest of the company can read, not a changelog for engineers. The audience is anyone who doesn't read diffs: support, sales, ops, whoever sits in the channel. They need to know what changed for them, in plain language. Not how it was built.
The deliverable is a ready-to-post Slack message: a fixed template, a handful of bullets, one emoji each, an optional closing line, always the channel-wide mention. Not the commit log with nicer punctuation. A translation of it, filtered down to what someone outside engineering would actually notice.
Two failure modes to avoid. A technical changelog with emoji stapled on: a bullet that names a class, a status code, or a function has failed, however it's formatted. And a post sent without asking: the draft stays a draft until the user has seen it and said so.
Invocation
/slack-changelog [optional scope]
Examples:
/slack-changelog/slack-changelog v2.4.0..HEAD- "écris le changelog Slack pour cette release"
- "prépare le message pour annoncer les dernières nouveautés côté connexion"
- "draft the Slack update for what shipped this week"
Step 1 — Resolve the scope
Know exactly which changes you're translating before you start drafting.
If the working directory holds a single repository, resolve the range the way branch-recap
does: an explicit range the user named, otherwise the latest tag through HEAD (the usual
release cut point), falling back to the merge-base against the closest integration branch
(origin/HEAD, origin/main, origin/develop, …) when the repo carries no tags.
If the working directory holds several independent repositories (a directory grouping multiple git repos, each releasing on its own), resolve the same range logic inside each one and read every repo's diff. Treat them as one release: assume they ship together and carry a shared level of coupling, not that only one of them matters. Don't ask which repo to use. Gather all of them, and say which repos you found before reading further.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 193 lines · 332 tokens per session scan A 99931f6592d1
slack-changelog is a skill published in the GitHub repository Malo-T/claude-toolbelt (2 stars, last pushed 22d ago), licensed MIT. It adds 332 tokens to every session and 2,354 once invoked, about $0.0017 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 2026-08-31.
Other skills, from other repositories
release
Automated release management - version updates, changelog generation, git tagging, and GitHub release creation.
git-for-research-code
When the user wants to version-control optimization research code - small commits per experiment change, tags for paper result snapshots, .gitignore for solver logs, linking result tables to commit hashes, and branch strategy for risky refactors. Also use when the user mentions "git workflow," "version control…
vienen-las-visitas
Use before work crosses to another person or system — opening a pull request, pushing a shared branch, requesting review, handing off to another agent, a demo, or a release. NOT for ordinary intermediate commits; this is the boundary-crossing gate, not a per-commit ritual.
github-audit
Audit GitHub repo health, auto-fix safe issues, run quality gates, deploy, and record decisions across runs. Use when asked to audit a repo, check repo/CI/dependency health, run pre-deploy quality checks, or ship after an audit.
release-plugin
A release procedure for publishing one DooTask plugin, an add-on for the DooTask application. It explains how the plugin's repository layout determines the release steps and how pushed Git tags trigger Docker Hub and app-store publishing.
publish
Publish oh-my-opencode to npm by triggering the GitHub Actions publish workflow and verifying its artifacts. Ship-only: never runs pre-publish-review or re-reviews merged code unless the user explicitly asks. Argument: . Triggers: publish, release, deploy, npm publish.