agents-at-scale-ark: Skill for Claude Code

.claude/skills/slack-announcement/SKILL.md

slack-announcement is a skill for Claude Code from mckinsey/agents-at-scale-ark. It costs 111 tokens per session (4,021 once invoked), scanned A, original, Apache-2.0.

A workflow for writing Slack announcements about Ark releases by collecting changes from the Ark core and marketplace repositories. It groups updates by theme and checks documentation links.

In plain words
What is it for?
Use it to prepare a full or short Slack release post for a specified version range or date period.
Why use it?
It avoids manually gathering release information from multiple repositories and helps keep announcements accurate and organized.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is mckinsey/agents-at-scale-ark's own configuration. It tells Claude Code how to work on agents-at-scale-ark itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agents-at-scale-ark configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mckinsey/agents-at-scale-ark. 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/mckinsey/agents-at-scale-ark/main/.claude/skills/slack-announcement/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mckinsey/agents-at-scale-ark

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.

agentmods badge for slack-announcement

README.md
[![agentmods](https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/slack-announcement/github.svg)](https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/slack-announcement)
Your own site
<a href="https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/slack-announcement"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/slack-announcement/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.

agentmods 80×15 button for slack-announcement

Your own site · 80×15
<a href="https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/slack-announcement"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/slack-announcement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,021 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00111 $0.04021
Opus 5 $0.00056 $0.02011
Sonnet 5 $0.00022 $0.00804
Haiku 4.5 $0.00011 $0.00402

Measured 8d ago against content hash 1f8944af3047, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

slack-announcement scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

The docs sites are a Next.js SPA on GitHub Pages. The published URL works once a browser runs the JS bundle, which is what real readers get when they click a Slack link. A direct `curl` fetches the SPA shell and often se
.claude/skills/slack-announcement/SKILL.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Slack announcement skill

Goal

A single Slack-ready post that summarises user-visible changes across Ark core and the Marketplace for a given window, grouped by theme, with markdown-style docs links, and a forward-looking section.

Inputs to confirm with the user

  • Window — explicit versions (e.g. v0.1.55 → v0.1.60) or a date range. If unclear, ask.
  • Depth — full long-form post, a short #announcements variant, or both (thread reply). Default full.

Process

1. Pull releases from BOTH repos

Always check both. A release in one repo often has no matching entry in the other.

# Ark core
gh release list --repo mckinsey/agents-at-scale-ark --limit 60
gh release view <tag> --repo mckinsey/agents-at-scale-ark --json body

# Marketplace (component-level tags, e.g. executor-claude-agent-sdk-v0.1.8)
gh release list --repo mckinsey/agents-at-scale-marketplace --limit 100 \
  --json tagName,publishedAt \
  --jq '.[] | select(.publishedAt >= "<start-date>")'
gh release view <tag> --repo mckinsey/agents-at-scale-marketplace --json body

For the marketplace, group component-level releases by component (e.g. executor-claude-agent-sdk: v0.1.0 → v0.1.9) and summarise the arc, not each patch.

2. Deduplicate and filter

  • Release-please regenerates the full CHANGELOG in some releases — compare gh api repos/<owner>/<repo>/compare/<prev>...<current> to find the genuinely new commits, not cumulative ones.
  • Drop ops/CI-only items: test migrations, dependency bumps, CVE patches (unless user-visible), flaky-CI fixes, release-please plumbing, deploy-pipeline fixes, SonarQube tweaks, mock-LLM work, install reliability patches.

3. Fetch docs links from the PR that shipped each feature

Release notes carry a PR number (... ([#1215](...))). The PR's own diff is the best source of truth for which docs page documents that feature. Don't guess the URL from the feature name — pull it from the PR.

3a. Find docs files changed in each PR

Read the full file on GitHub · 294 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.

  1. 8d ago First seen · 294 lines · 111 tokens per session scan A 1f8944af3047

Subscribe to this mod's changes

slack-announcement is a skill published in the GitHub repository mckinsey/agents-at-scale-ark (422 stars, last pushed yesterday), licensed Apache-2.0. It adds 111 tokens to every session and 4,021 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.