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 tomeraitz/claude-slack-bridge --skill verify-bridgegit clone --depth 1 https://github.com/tomeraitz/claude-slack-bridgeWrote 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/tomeraitz/claude-slack-bridge/verify-bridge)<a href="https://agentmods.dev/skills/tomeraitz/claude-slack-bridge/verify-bridge"><img src="https://agentmods.dev/badge/skills/tomeraitz/claude-slack-bridge/verify-bridge/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/tomeraitz/claude-slack-bridge/verify-bridge"><img src="https://agentmods.dev/badge/skills/tomeraitz/claude-slack-bridge/verify-bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00110 | $0.00454 |
| Opus 5.5 | $0.00044 | $0.00182 |
| Sonnet 5.5 | $0.00022 | $0.00091 |
| Haiku 4.5 | $0.00011 | $0.00045 |
Grade A, and why
verify-bridge 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 2mo 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.
What it actually says
verify-bridge — confirm the Slack bridge MCP is declared in this repo
Verify that mcp__claude-slack-bridge is installed in the current repo by reading cwd/.mcp.json. The file must exist and must contain a server entry whose key is claude-slack-bridge (the MCP tool prefix mcp__claude-slack-bridge__* is derived from this key).
import json, os
mcp_path = os.path.join(os.getcwd(), ".mcp.json")
if not os.path.exists(mcp_path):
# hard fail — see message below
...
with open(mcp_path) as f:
cfg = json.load(f)
if "claude-slack-bridge" not in (cfg.get("mcpServers") or {}):
# hard fail — see message below
...
If either check fails, print this exact message and exit non-zero. Do not offer to write the entry yourself, do not continue:
mcp__claude-slack-bridgeis not installed in this repo. Add aclaude-slack-bridgeentry undermcpServersin.mcp.json(see the project README for the exact docker-exec snippet), then re-run the calling workflow.
Do not check whether the bridge container is running — only that the repo declares the server. Runtime health is the caller's problem, not this skill's.
On success, print one short confirmation line and exit zero:
verify-bridge: ok (claude-slack-bridge declared in .mcp.json)
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.
- 2mo ago First seen · 32 lines · 110 tokens per session scan A 0b208020b255
verify-bridge is a skill published in the GitHub repository tomeraitz/claude-slack-bridge (35 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 454 once invoked, about $0.0004 per session on Opus 5.5. 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.
verify-bridge compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| verify-bridgetomeraitz/claude-slack-bridge | Skill | 35 | 1mo ago | MIT | A | 110 | Claude Code |
| slack-expertpersonamanagmentlayer/pcl | Skill | 44 | 14d ago | Apache-2.0 | A | 69 | Claude Code |
| accesspierreraii/claude-slack-bridge | Skill | 1 | 6mo ago | Apache-2.0 | A | 43 | Claude Code |
| configurepierreraii/claude-slack-bridge | Skill | 1 | 6mo ago | Apache-2.0 | B | 56 | Claude Code |
| opik-diagnosecomet-ml/opik-mcp | Skill | 226 | 3d ago | Apache-2.0 | A | 187 | Claude Code |
| llm-wikiCoWork-OS/CoWork-OS | Skill | 542 | today | MIT | A | 27 | Claude Code, Codex |
| simplifyCoWork-OS/CoWork-OS | Skill | 542 | today | MIT | A | 24 | Claude Code, Codex |