A release procedure for SlackCLI, a command-line tool, covering the work from reviewing commits through publishing a new version. It uses Semantic Versioning, a version-numbering system, and separates the reversible pull request from the final tag that publishes binaries and updates the Homebrew package source.

It is for surveying changes, choosing a version bump, opening the release issue and pull request, updating the changelog, checking signatures, and publishing the confirmed release.

It reduces release errors involving version mismatches, unsigned commits, missing linked issues, and premature publishing. It also requires human confirmation before the irreversible tagging step.

How shaharia-lab/slackcli configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to shaharia-lab/slackcli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/shaharia-lab/slackcli/main/.claude/skills/release/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/shaharia-lab/slackcli

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/shaharia-lab/slackcli/release/github.svg)](https://agentmods.dev/skills/shaharia-lab/slackcli/release)

Your own site

<a href="https://agentmods.dev/skills/shaharia-lab/slackcli/release"><img src="https://agentmods.dev/badge/skills/shaharia-lab/slackcli/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/shaharia-lab/slackcli/release"><img src="https://agentmods.dev/badge/skills/shaharia-lab/slackcli/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,894 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00087	$0.01894
Opus 5.5	$0.00035	$0.00758
Sonnet 5.5	$0.00017	$0.00379
Haiku 4.5	$0.00009	$0.00189

Measured 1mo ago against content hash ccde39ee519c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

.claude/skills/release/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cutting a SlackCLI release

A release is two separate things, in this order:

A PR onto main that bumps package.json and promotes the CHANGELOG. Reversible.
An annotated tag pushed to that merged commit. This is the irreversible, outward-facing step — release.yml builds and publishes public binaries, and force-updates the Homebrew tap at shaharia-lab/homebrew-tap.

Never do step 2 without explicit human confirmation. See Gate before tagging.

Hard constraints

These are the ways a release goes wrong. Check them, don't rediscover them.

release.yml fails when the tag disagrees with package.json (#82). The bump must be merged into main before the tag is pushed. Fixing it after the fact means bumping main and then deleting and re-pushing the tag.
main requires signed commits, with no bypass actors — an unsigned commit makes the PR unmergeable for anyone, including admins. Verify the release commit carries a signature.
The repository constitution in CLAUDE.md applies to the release PR too: it needs a linked GitHub issue carrying ready-for-pr before the PR is opened. pr-linked-issue.yml enforces the link as a required check.
main requires one approving review, and an agent cannot approve its own PR. So gh pr merge reports BLOCKED / REVIEW_REQUIRED even when every check is green. Unblocking it is the maintainer's decision, taken one of two ways — a review, or an explicit instruction to merge with --admin. Never pick --admin on your own initiative; surface the block and let the maintainer choose. dismiss_stale_reviews_on_push is on, so any push after an approval discards it — get the branch final before asking for review.
Pre-commit hooks block direct commits to main. Always work on a branch.
A merged PR does not guarantee a CHANGELOG entry. Reconcile commits against [Unreleased] yourself — the mrkdwn fix in #96 landed with no entry and had to be backfilled at v0.9.0.
bun may not be on PATH in a non-interactive shell. If bun is not found, use export PATH="$HOME/.bun/bin:$PATH".

Read the full file on GitHub · 130 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.

1mo ago Changed ccde39ee519c
2mo ago First seen · 130 lines · 87 tokens per session scan A 1e5e8bbd2d4d

Subscribe to this mod's changes

release is a skill published in the GitHub repository shaharia-lab/slackcli (266 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 1,894 once invoked, about $0.0003 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.

Git and workflow Releases ai-tools automation cli slack slack-api slack-cli

release next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
releaseshaharia-lab/slackcli	Skill	266	yesterday	MIT	A	87	Claude Code
git-flow-prsoulcodex/agentic	Skill	10	7d ago	MIT	A	103	Claude Code, Codex
write-changelogsoulcodex/agentic	Skill	10	7d ago	MIT	A	73	Claude Code, Codex
gspdev-changelogjubscodes/get-shit-pretty	Skill	55	5mo ago	MIT	A	38	Claude Code
gspdev-publishjubscodes/get-shit-pretty	Skill	55	5mo ago	MIT	A	28	Claude Code
verify-cliNimbleBrainInc/mpak	Skill	14	1mo ago	none	A	23	Claude Code
od-plugin-publish-githubwolfenazz/YzPzCode	Skill	20	yesterday	Apache-2.0	B	24	Claude Code, Codex

slackcli: Skill for Claude Code