Borrowing it
Nothing to install: this file belongs to samarthanalytics-sj/samarth-analytics-mcp. 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/samarthanalytics-sj/samarth-analytics-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/samarthanalytics-sj/samarth-analytics-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/samarthanalytics-sj/samarth-analytics-mcp/claude-md)<a href="https://agentmods.dev/instructions/samarthanalytics-sj/samarth-analytics-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/samarthanalytics-sj/samarth-analytics-mcp/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/samarthanalytics-sj/samarth-analytics-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/samarthanalytics-sj/samarth-analytics-mcp/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 | $0.01517 | $0.01517 |
| Opus 5.5 | $0.00607 | $0.00607 |
| Sonnet 5.5 | $0.00303 | $0.00303 |
| Haiku 4.5 | $0.00152 | $0.00152 |
Grade A, and why
samarth-analytics-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 2d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project-specific guidance for working in this repo with Claude Code (Desktop / App / CLI). These instructions override default behavior — follow them.
What this repo is
Samarth Analytics MCP — a production MCP server for the Google Tag Manager API v2, plus read-only GA4 (Admin + Data API) tooling, and a white-label customer portal that runs GTM/Consent Mode v2 audits.
Layout:
src/— the MCP server (stdio + HTTP transports, tools, guardrails, auth).apps/portal/— the customer portal. Vite client + Express dev server, deployed to Vercel as serverless functions underapps/portal/api/.apps/portal/shared/— framework-free audit engines (incl. the Consent Mode v2 engine and its test suite).apps/runtime-worker/— read-only headless-Chromium capture worker. Not for Vercel — needs a real browser host (Render/Fly/Railway/VPS).apps/web-audit-mcp/— a second MCP server (stdio + Streamable HTTP) with a built-in site audit agent: Playwright crawl, form inventory, consent-banner (CMP) interaction, Consent Mode v2 compliance findings, and optional GTM container reconciliation. Reuses the shared consent engine; SSRF guard mirrors the runtime worker. Ships a Dockerfile (Playwright base image, HTTP transport) for hosted deploys — not for Vercel either. The autonomous audit agent's only permitted page interaction is clicking consent-banner controls — never submit forms or click anything else from those tools.- Exception — the
verifytool (apps/web-audit-mcp/src/verify/, the TagDrishti tag verification engine): operator-driven, it performs the spec-supplied interactions including real form submits to prove trigger-fired events (user-authorized 2026-07-04). OFF by default, gated behindWEB_AUDIT_ENABLE_VERIFY=true; thesamarth-verifyCLI is an explicit local invocation and needs no flag. Client-side only — server-side verification (CAPI/sGTM/Measurement Protocol) is a documented non-goal with an empty stub, never claimed in output. Do NOT widen the audit agent's interaction surface, and do NOT flip the verify flag default, without an explicit user request.
- Exception — the
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.
- 2d ago Changed cb1a97565282
- 2mo ago First seen · 130 lines · 1,517 tokens per session scan A a07f149341ef
samarth-analytics-mcp CLAUDE.md is an instructions file published in the GitHub repository samarthanalytics-sj/samarth-analytics-mcp (3 stars, last pushed 3d ago), licensed MIT. It adds 1,517 tokens to every session, about $0.0061 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 2026-08-31.
samarth-analytics-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| samarth-analytics-mcp CLAUDE.mdsamarthanalytics-sj/samarth-analytics-mcp | Instructions file | 3 | 3d ago | MIT | A | 1,517 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |