Borrowing it
Nothing to install: this file belongs to py-zoid/mcp-tenderly. 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/py-zoid/mcp-tenderly/main/CLAUDE.mdgit clone --depth 1 https://github.com/py-zoid/mcp-tenderlyWrote 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/py-zoid/mcp-tenderly/claude-md)<a href="https://agentmods.dev/instructions/py-zoid/mcp-tenderly/claude-md"><img src="https://agentmods.dev/badge/instructions/py-zoid/mcp-tenderly/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 | $0.01810 | $0.01810 |
| Opus 5 | $0.00905 | $0.00905 |
| Sonnet 5 | $0.00362 | $0.00362 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
mcp-tenderly 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 7d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-tenderly
MCP server exposing Tenderly transaction simulation and trace debugging over the
stdio transport. See README.md for user-facing setup and the tool reference.
Commands
npm run verify # everything CI runs, in CI's order
npm test # unit tests (excludes the stdio smoke test)
npm run test:smoke # builds, then drives dist/index.js over a real stdio transport
npm run typecheck
npm run lint
Layout
src/
index.ts entry point: config, stdio transport, signals
server.ts builds the McpServer and registers tools
config.ts the only module that reads process.env
logger.ts structured NDJSON logging to stderr
errors.ts error taxonomy, retriable vs terminal, remediation text
tenderly/
client.ts REST client: auth, timeout, bounded retry
schemas.ts zod shapes for every response
format.ts payload to LLM-readable digest <- the point of the server
networks.ts chain name to chain id
tools/
common.ts shared input schemas, runTool boundary
*.ts one file per tool
Constraints worth knowing before you change anything
Stdout belongs to the protocol. Under stdio, stdout carries newline-delimited
JSON-RPC frames. A single console.log anywhere in src/ corrupts the framing
and the host silently drops the server. All diagnostics go through logger.ts,
which writes to stderr. tests/stdio-smoke.test.ts asserts that stdout contains
nothing but valid frames — that test exists specifically to catch this.
Response schemas are intentionally lenient. Every response shape in
schemas.ts is a z.looseObject with almost every field optional. This is not
laziness. The Tenderly API is not version-locked, and its payloads genuinely
differ between simulation_type values, between /simulate and
/simulations/{id}, and between verified and unverified contracts. Strict
parsing would turn a harmless new field or an absent optional block into a hard
tool failure — much worse than a formatter rendering "unknown" for one line. The
invariant that is kept: nothing reaches the formatter without passing a schema,
so the formatter never indexes into any.
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.
- 7d ago First seen · 143 lines · 1,810 tokens per session scan A 16d61ebbc3a7
mcp-tenderly CLAUDE.md is an instructions file published in the GitHub repository py-zoid/mcp-tenderly (0 stars, last pushed 18d ago), licensed MIT. It adds 1,810 tokens to every session, about $0.0090 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
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).
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.
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.