Borrowing it
Nothing to install: this file belongs to slack-samples/bolt-js-slack-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/slack-samples/bolt-js-slack-mcp-server/main/.agents/skills/test-slack-app/SKILL.mdgit clone --depth 1 https://github.com/slack-samples/bolt-js-slack-mcp-serverWrote 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-js-slack-mcp-server/test-slack-app)<a href="https://agentmods.dev/skills/slack-samples/bolt-js-slack-mcp-server/test-slack-app"><img src="https://agentmods.dev/badge/skills/slack-samples/bolt-js-slack-mcp-server/test-slack-app/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-js-slack-mcp-server/test-slack-app"><img src="https://agentmods.dev/badge/skills/slack-samples/bolt-js-slack-mcp-server/test-slack-app.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 | $0.00111 | $0.02204 |
| Opus 5.5 | $0.00044 | $0.00882 |
| Sonnet 5.5 | $0.00022 | $0.00441 |
| Haiku 4.5 | $0.00011 | $0.00220 |
Grade A, and why
test-slack-app 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 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.
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.
This is a copy
100% identical to test-slack-app — 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Slack App
Help a developer confirm that a Slack app they already built actually works. This is the last step of the build loop, after the create-slack-app skill scaffolds an app and the slack-cli skill runs it.
The approach is simple and safe:
- Run the app in a developer sandbox or a Free Team: a sandbox for preference, or a Free Team the developer created for this. Never a workspace with real coworkers in it.
- Read the app's source to learn what it actually listens for.
- Hand the developer concrete steps to perform in Slack, then help them confirm the app responds.
This is guided manual checking, not an automated test suite: you drive the setup and tell the developer what to type or click, and they confirm what they see. It works best for apps managed by the Slack CLI; there is a best-effort path for plain Bolt apps in Step 2.
Step 1: Set Up a Safe Place to Test
1a. Detect the Slack CLI
Load the slack-cli skill (with your skill tool, if you have one) before running any command, and follow its Step 1: Detect the Slack CLI to check whether the public Slack CLI is installed and resolve its command name. Don't check for the CLI yourself first: a slack on PATH isn't always the public CLI, and that step tells them apart. The fingerprint check, alias fallback, and install instructions all live there; do not duplicate them here. Refer to the resolved command as SLACK_CMD throughout. If the CLI is not installed, guide the developer through that same step to install it, since running the app needs it.
1b. Make sure there is a safe workspace to test in
Testing belongs in a workspace nobody is working in: a developer sandbox for preference, or a Free Team the developer created for this. Never a workspace with real coworkers in it.
- Explain it from the live docs, not from here. Use the
slack-docsskill to fetch and summarize https://docs.slack.dev/tools/developer-sandboxes.md, so the recommendation always reflects the current docs rather than a copy that drifts out of date. Tell the developer that Slack recommends a sandbox for building and testing apps. - Find the current target. Run
SLACK_CMD auth listfor the authenticated workspaces and their team IDs, and, from the project directory,SLACK_CMD app listfor the apps already installed and their IDs. - Confirm the target is safe. The CLI cannot tell a sandbox, a Free Team, and a workspace full of real users apart, so ask the developer which one they are pointed at. A sandbox or a Free Team they created for this is fine. A workspace with coworkers in it is not: stop and get them onto one of the other two.
- If there is no safe target yet, set one up with the
create-slack-appskill (Step 3: Choose Where to Install the App), which owns the ranked targets, thesandbox list/sandbox createflow, and the Developer Program links. Either path finishes in the browser, so have the developer come back here once the workspace exists and they have logged into it.
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 · 112 lines · 111 tokens per session scan A 37252264d344
test-slack-app is a skill published in the GitHub repository slack-samples/bolt-js-slack-mcp-server (17 stars, last pushed yesterday), licensed MIT. It adds 111 tokens to every session and 2,204 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to test-slack-app, differing in 0 lines, and is treated as a copy.
test-slack-app compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| test-slack-appslack-samples/bolt-js-slack-mcp-server | Skill | 17 | yesterday | MIT | A | 111 | Claude Code, Codex |
| create-verification-skillYeachan-Heo/oh-my-claudecode | Skill | 41k | today | MIT | A | 45 | Claude Code |
| verify-omnigentomnigent-ai/omnigent | Skill | 11k | today | Apache-2.0 | A | 100 | Claude Code, Codex |
| test-masterJeffallan/claude-skills | Skill | 12k | yesterday | MIT | A | 104 | Claude Code |
| eval-dataset-designbojieli/ai-agent-book | Skill | 59k | 1mo ago | Apache-2.0 | A | 138 | Claude Code, Codex |
| dogfoodcallstack/agent-device | Skill | 5.4k | today | MIT | A | 55 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | today | MIT | A | 68 | Claude Code, Codex |