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 slack-samples/bolt-ts-starter-template --skill block-kitgit clone --depth 1 https://github.com/slack-samples/bolt-ts-starter-templateWrote 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/slack-samples/bolt-ts-starter-template/block-kit)<a href="https://agentmods.dev/skills/slack-samples/bolt-ts-starter-template/block-kit"><img src="https://agentmods.dev/badge/skills/slack-samples/bolt-ts-starter-template/block-kit/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/slack-samples/bolt-ts-starter-template/block-kit"><img src="https://agentmods.dev/badge/skills/slack-samples/bolt-ts-starter-template/block-kit.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 | $0.00112 | $0.04642 |
| Opus 5.5 | $0.00045 | $0.01857 |
| Sonnet 5.5 | $0.00022 | $0.00928 |
| Haiku 4.5 | $0.00011 | $0.00464 |
Grade A, and why
block-kit 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 yesterday.
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.
Prefer the Slack CLI when it's available, since it reuses the slack-cli skill's CLI detection and needs no token wrangling. If the CLI isn't installed, fall back to curl. Both call the same public method and return the s This is a copy
89% identical to block-kit — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Block Kit
Help the developer build a rich Block Kit layout. If $0 is exactly message, modal, or home-tab, treat it as the target surface. Otherwise (including if it's empty or any other value), ignore it and determine the surface in Step 1.
This skill walks through surface selection, layout planning, JSON generation, and validation. Block types, elements, and fields come from the live docs (see Source of Truth below) — discover them and read each component's schema there, never from memory.
Common Block Kit mistakes (and why): A few errors recur often enough to flag up front. Most others are caught by
blocks.validatein Step 5, so lean on validation rather than memorizing rules.
"type": "text"is not a thing. Text is a composition object:{ "type": "plain_text", "text": "..." }or{ "type": "mrkdwn", "text": "..." }.markdownis a block type, not a text type. Amarkdownblock holds standard markdown; text objects inside other blocks usemrkdwn(see mrkdwn vs. themarkdownblock in Step 4). Slack'smrkdwnis*bold*/_italic_/~strike~, not**bold**.- Messages need a top-level
textfallback.blocks.validatewon't flag a missing one, but notifications and screen readers display it instead of the blocks — so summarize what the layout conveys rather than leaving it empty.
Source of Truth: the Live Docs
Every block, element, and composition object is documented on docs.slack.dev. Append .md to any reference URL to fetch it as markdown with WebFetch (no auth required).
- Master index: the authoritative list of every block, block element, and composition object, each linking to its own page:
https://docs.slack.dev/reference/block-kit.md. WebFetch it to confirm a type exists and to get the link to its page. - Per-component pages carry the full field schema (a fields table with required/optional flags and constraints, plus JSON examples):
- Blocks:
https://docs.slack.dev/reference/block-kit/blocks/<slug>-block.md - Block elements:
https://docs.slack.dev/reference/block-kit/block-elements/<slug>-element.md - Composition objects:
https://docs.slack.dev/reference/block-kit/composition-objects/<slug>.md
- Blocks:
- The slug is not always the type name. For example
datepickermaps todate-picker-element.md, and every*_selectmenu (static_select,users_select,multi_channels_select, and so on) is documented onselect-menu-element.md. When unsure of a slug, follow the link from the master index rather than building the URL by hand. - Surface payload structure lives in the surface guides: messages at
https://docs.slack.dev/messaging/formatting-message-text.md, modals athttps://docs.slack.dev/surfaces/modals.md, and Home tabs athttps://docs.slack.dev/surfaces/app-home.md.
What ships with it
7 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.
- yesterday First seen · 285 lines · 112 tokens per session scan A d9d259757ccc
block-kit is a skill published in the GitHub repository slack-samples/bolt-ts-starter-template (65 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 4,642 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 89% identical to block-kit, differing in 0 lines, and is treated as a copy.
block-kit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| block-kitslack-samples/bolt-ts-starter-template | Skill | 65 | yesterday | MIT | A | 112 | Claude Code |
| imagegenopenai/codex | Skill | 136k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 14k | today | CC0-1.0 | A | 113 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |