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/slackapi/slack-skills-plugin/slack-docsnpx skills add slackapi/slack-skills-plugin --skill slack-docsgit clone --depth 1 https://github.com/slackapi/slack-skills-pluginWhat 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 | $0.00057 | $0.02240 |
| Opus 5 | $0.00028 | $0.01120 |
| Sonnet 5 | $0.00011 | $0.00448 |
| Haiku 4.5 | $0.00006 | $0.00224 |
Grade A, and why
slack-docs 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 2d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slack Platform Documentation
Help the developer find the right page on the official Slack documentation site (https://docs.slack.dev) and read it as clean markdown, so answers come from the live docs rather than memory. The site exposes three machine-readable surfaces an agent can use directly, with no authentication and no Slack workspace:
- A search API method:
GET https://docs.slack.dev/api/v1/search?query=<q>&category=<c>returns ranked page hits as JSON. Scope every search with acategory(guides, reference, a specific SDK, etc.); an uncategorized search skews heavily toward SDK pages. - Per-page markdown: every page is available at its URL +
.md(e.g./quickstart.md). - Index files:
/llms.txt(a curated overview) and/llms-sitemap.md(a list of every markdown page).
If $0 is provided, it is either a docs.slack.dev URL (jump to the Fast Path) or a topic to search (start at Step 1). For a broad "how do I build X on Slack?" question rather than one specific page, read https://docs.slack.dev/llms.txt first; it is a curated, LLM-oriented overview of the platform and the recommended build path.
Critical rules:
- The docs are the source of truth. Do not answer a factual question about the Slack platform from memory; discover the page, fetch it, then answer from what it says.
- Prefer the
.mdversion of any page over the HTML version. It is cleaner for reading and quoting.- Every fetched markdown page begins with a
Source: <url>line. Keep that URL so you can cite the page back to the developer.
DO NOT rules:
- DO NOT invent documentation URLs. Get them from the search API, the sitemap, or a link the developer gave you then verify by fetching.
- DO NOT paraphrase a page you have not actually fetched. If a fetch fails, say so rather than filling the gap from memory.
- DO NOT assume every URL has a
.mdversion. If a fetch returns an error, fall back to the search API or the sitemap (Step 1) rather than guessing another URL.
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.
- 2d ago First seen · 125 lines · 57 tokens per session scan A e77cf7647c45
slack-docs is a skill published in the GitHub repository slackapi/slack-skills-plugin (113 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 2,240 once invoked, about $0.0003 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
explainer
Create explainer videos with narration and AI-generated visuals. Triggers on: "解说视频", "explainer video", "explain this as a video", "tutorial video", "introduce X (video)", "解释一下XX（视频形式）".
explain-code
Explains code with visual diagrams and analogies. Use when explaining how code works, walking through a codebase area, or when the user asks "how does this work?" Don't use for modifying code, fixing bugs, generating new implementations, or multi-session concept learning (use /teach).
practice-setup
This skill should be used when the user runs "/balanced-scorecard:practice-setup" (with optional --quick, --full, --redo, --check-integrations, or --resume), asks to "set up the balanced-scorecard plugin," "teach Claude our strategy map," or wants to redo that setup after the sector, perspective model, or cadence…
teach
Teach the user a new skill or concept, within this workspace.
change-quiz
Generate one droppable self-contained HTML report (never a Cursor canvas) explaining a change set, ending with a quiz the user must pass before merging. Use when the user says "quiz me", "考考我", "change quiz", "变更测验", or, after a large change or session, wants to verify they truly understand it — e.g. "merge…
jupyter
Jupyter notebooks for interactive computing. Use for data exploration.