Borrowing it
Nothing to install: this file belongs to TLS-Radar/tlsradar-claude-plugin. 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/TLS-Radar/tlsradar-claude-plugin/main/CLAUDE.mdgit clone --depth 1 https://github.com/TLS-Radar/tlsradar-claude-pluginWrote 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/tls-radar/tlsradar-claude-plugin/claude-md)<a href="https://agentmods.dev/instructions/tls-radar/tlsradar-claude-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/tls-radar/tlsradar-claude-plugin/claude-md/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/instructions/tls-radar/tlsradar-claude-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/tls-radar/tlsradar-claude-plugin/claude-md.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 | $0.09562 | $0.09562 |
| Opus 5 | $0.04781 | $0.04781 |
| Sonnet 5 | $0.01912 | $0.01912 |
| Haiku 4.5 | $0.00956 | $0.00956 |
Grade D, and why
tlsradar-claude-plugin CLAUDE.md scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
- **Anonymous attribution does NOT use an env var or header.** The `scan`/`create_certificate` commands mint `~/.config/tlsradar/install_id` (there is no hook - Round 8), read that file, and pass it as the `client_id` ar Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
**Shell-injection boundary (0.6.1, PR review follow-up).** Validating inside Python isn't enough if the *caller* pastes `record.name`/`record.value` into a Bash command - shell expansion of `$(...)`/backticks/`;` happens Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
20. **DNS-provider automation is tested code, not prose (#2).** `scripts/dns_provider.py` (+ `dns_provider_test.py`) owns the gotcha-prone logic - registrable-root extraction, the Cloudflare payload, Route 53's mandatory How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin context for future coding agents
If you're a Claude Code (or other AI) instance working in this repo, this file is the fastest way to get your bearings. Read it first.
What this plugin is for
It's the free, top-of-funnel entry point to TLS Radar: give developers genuinely useful free tools (scanning, Let's Encrypt issuance) with no account, and offer the people who want it an easy path into ongoing monitoring. Design choices that matter:
- Free anonymous scans and free Beacon cert issuance let users try the plugin without an account - low friction is the whole point.
- When a cert is issued, the optional cert → monitoring handoff is what turns a one-off Beacon user into a TLS Radar monitoring user (with the user's knowledge - the email's dual use is disclosed at collection, marketing stays opt-in).
- Hitting the free monitor cap surfaces a friendly upgrade suggestion (Starter, ~$10/mo) - server-gated, shown once, never pushy, with the actual price coming from the server payload (see the funnel-etiquette rules in
skills/certificate-monitoring/SKILL.md).
When you change something, keep the experience low-friction and honest: useful free tools first, conversion as a side effect of value delivered, never a dark pattern. Don't add friction at install, login, or cap-hit.
Architecture in one paragraph
There is no binary. The plugin is pure configuration + Markdown. Claude Code's MCP client talks to one remote MCP server - tlsradar.com/api/v1/mcp. Certificate issuance is proxied server-side through that server to Beacon (beacon.tlsradar.com), so the plugin holds a single connection and a single auth model. Public tools (scan, cert_*) need no auth; everything else uses Claude Code's built-in OAuth 2.0 + PKCE flow via /mcp (the plugin registers dynamically, RFC 7591, the first time the user runs /mcp). There is no client-facing Beacon connection and no BEACON_PLUGIN_TOKEN anymore - TLS Radar's Beacon::Client calls Beacon's REST API server-to-server with the (intentionally public) token it already holds.
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 · 271 lines · 9,562 tokens per session scan D 132688662b42
tlsradar-claude-plugin CLAUDE.md is an instructions file published in the GitHub repository TLS-Radar/tlsradar-claude-plugin (0 stars, last pushed 2mo ago), licensed MIT. It adds 9,562 tokens to every session, about $0.0478 per session on Opus 5. A static security scan graded it D with 3 findings (reads mcp configuration, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.