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 azmym/agent-skills --skill slackgit clone --depth 1 https://github.com/azmym/agent-skillsWrote 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/azmym/agent-skills/slack)<a href="https://agentmods.dev/skills/azmym/agent-skills/slack"><img src="https://agentmods.dev/badge/skills/azmym/agent-skills/slack/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/azmym/agent-skills/slack"><img src="https://agentmods.dev/badge/skills/azmym/agent-skills/slack.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 | $0.00125 | $0.03408 |
| Opus 5 | $0.00063 | $0.01704 |
| Sonnet 5 | $0.00025 | $0.00682 |
| Haiku 4.5 | $0.00013 | $0.00341 |
Grade A, and why
slack 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.
| Token | `token` | Direct curl calls using Chrome session tokens. Fast. macOS only. | How it starts
The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slack Web API Skill
Interact with Slack: read, write, search, react, pin, and manage conversations via the Web API.
IMPORTANT: First-Use Initialization
Before executing any Slack operation, check if the mode config file exists:
cat ~/.agents/config/slack/config.env
If the file does not exist (or does not contain SLACK_MODE), you must ask the user which mode they want to use. Present these three options:
- Token (macOS only): Extracts session tokens directly from Chrome. Fastest option. Requires Chrome with Slack open, AppleScript enabled, and
uvxinstalled. - Browser (cross-platform): Uses a local Playwright browser to make API calls. Works on macOS, Linux, and Windows. Requires Node.js 18+. Supports SSO and 2FA login.
- Auto-detect (recommended): Automatically uses browser mode if a Playwright session exists, otherwise falls back to token mode. Best of both worlds.
Once the user selects a mode, save it immediately:
mkdir -p ~/.agents/config/slack
echo 'SLACK_MODE=<selected_value>' > ~/.agents/config/slack/config.env
Where <selected_value> is token, browser, or auto.
After saving, never ask again. On all subsequent invocations, the config file will exist and the skill will use the saved mode automatically.
If the user selected browser mode, also run the browser session setup:
{SKILL_DIR}/scripts/slack-browser-session.sh login-manual
This opens a visible browser for the user to log in to Slack (supports SSO/2FA). The session is saved and reused for all future API calls.
Mode Selection
The skill supports three modes. Set via ~/.agents/config/slack/config.env or the SLACK_MODE environment variable:
| Mode | Value | Behavior |
|---|---|---|
| Token | token |
Direct curl calls using Chrome session tokens. Fast. macOS only. |
| Browser | browser |
API calls through a local Playwright browser session. Cross-platform. |
| Auto-detect | auto |
Use browser if session exists; falls back to token on auth failure. (default) |
What ships with it
9 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.
- metadata.json 424 B
- references/api-methods.md 6.7 KB
- references/browser-mode.md 7.3 KB
- scripts/package.json 81 B
- scripts/playwright-bridge.js 11 KB runs code
- scripts/slack-api.sh 6.8 KB runs code
- scripts/slack-browser-api.sh 255 B runs code
- scripts/slack-browser-session.sh 7.8 KB runs code
- scripts/slack-token-refresh.sh 5.0 KB runs code
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.
- 8d ago First seen · 359 lines · 125 tokens per session scan A 236f39bd1a34
slack is a skill published in the GitHub repository azmym/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 125 tokens to every session and 3,408 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 2026-08-31.
Other skills, from other repositories
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".
notifications
Send notifications through the unified notification router.
gmail-trigger
Beta. Act on new Gmail as it arrives: get pinged only for urgent mail, digest newsletters, forward invoices — any standing instruction, across one or several accounts.
start-the-day
An on-demand personal daily briefing — weather, headlines, the shape of your day, and one thing worth your attention — in a sharp executive-assistant voice. The general-purpose morning brief; richer work or admin digests compose it as their general layer.
offer-toolkit-skill
A set of job-search tools covering the path from finding a vacancy to accepting an offer. It includes separate tools for job searches, job-description analysis, tailored resumes, behavioral interviews, offer comparisons, and salary negotiation.