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 instructions/groupthink-dev/tailscale-blade-mcp/claude-mdgit clone --depth 1 https://github.com/Groupthink-dev/tailscale-blade-mcpWrote 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/instructions/groupthink-dev/tailscale-blade-mcp/claude-md)<a href="https://agentmods.dev/instructions/groupthink-dev/tailscale-blade-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/groupthink-dev/tailscale-blade-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.00615 | $0.00615 |
| Opus 5 | $0.00308 | $0.00308 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
tailscale-blade-mcp CLAUDE.md 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 5d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tailscale-blade-mcp
Tailscale network monitoring and security MCP. 19 tools, token-efficient output.
Architecture
src/tailscale_blade_mcp/
├── server.py — FastMCP server, 19 @mcp.tool decorators
├── client.py — TailscaleClient wrapping httpx async, credential scrubbing
├── formatters.py — Token-efficient output (pipe-delimited, null omission, relative times)
├── models.py — TailscaleConfig, write gate
└── auth.py — BearerAuthMiddleware for HTTP transport
Dev commands
make install-dev # Install with dev + test deps
make test # Unit tests (no API access needed)
make check # ruff lint + format + mypy
make run # Start MCP server (stdio)
Key patterns
- httpx async — direct REST API calls, no third-party Tailscale library
- Tailnet
-shorthand — auto-detects from API key, no explicit tailnet config needed nodeIdpreferred — newer device identifier format (not legacyid)- Write gate —
TAILSCALE_WRITE_ENABLED=truerequired for mutations, destructive ops also needconfirm=true - ACL apply —
ts_acl_setvalidates first, then POSTs with optimistic concurrency: it auto-fetches the current ETag and sendsIf-Matchso a concurrent admin edit 412s instead of clobbering (bypass viaallow_overwrite_concurrent=true).client.get_acl_with_etag()surfaces the ETag;client.set_acl(policy, if_match=...)returns(applied_policy, new_etag). Apply needs a token with policy-file write scope (read-only keys 403). - Credential scrubbing — 4 regex patterns strip API keys, Bearer tokens from errors
- No pagination — Tailscale API returns all results in one response
API reference
- Base URL:
https://api.tailscale.com/api/v2/ - Auth:
Authorization: Bearer tskey-api-... - Tailnet path:
/tailnet/{tailnet}/...(use-for auto-detect) - Devices:
/tailnet/-/devices?fields=all - Device detail:
/device/{nodeId}?fields=all - ACL read:
GET /tailnet/-/acl(response carriesETag) - ACL validate:
POST /tailnet/-/acl/validate - ACL apply:
POST /tailnet/-/acl(Content-Type: application/json, optionalIf-Match: <etag>; needs policy-file write scope)
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.
- 5d ago First seen · 49 lines · 615 tokens per session scan A d3a581322a10
tailscale-blade-mcp CLAUDE.md is an instructions file published in the GitHub repository Groupthink-dev/tailscale-blade-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 615 tokens to every session, about $0.0031 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 2026-08-31.
Other instructions, from other repositories
aks-mcp copilot-instructions.md
Copilot instructions for Azure/aks-mcp, covering copilot instructions, project overview, architecture, high-level structure and key components.
xtnd-mcp-one CLAUDE.md
Claude Code instructions for XTND-DYNAMICS/xtnd-mcp-one, covering claude.md — xtnd-mcp-one, golden rules and commands.
wireshark-mcp CLAUDE.md
Claude Code instructions for wgthomas/wireshark-mcp, covering wireshark mcp, quick start, tools (20 total), discrete (15) and workflows (5).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).
bray AGENTS.md
AGENTS.md instructions for forgesworn/bray, covering agents.md — nostr-bray, what this is, build & test, architecture and tool groups.