tell-core-engine

tell-core-engine is a cursor rule for Cursor from ashishpatill/tell-proof. It costs 0 tokens per session (201 once invoked), scanned A, original, MIT.

A reference guide for understanding errors and warnings from an MCP definition linter. MCP is a standard for defining tools, data resources, and prompts that AI agents can use.

In plain words
What is it for?
Use it when `bun run lint:mcp` or `bun run devcheck` reports problems such as invalid schemas, names, server metadata, or format mismatches.
Why use it?
It explains what each reported rule means, how serious it is, and what kind of correction is expected.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/ashishpatill/tell-proof/tell-core-engine
Clone the repo
git clone --depth 1 https://github.com/ashishpatill/tell-proof

Made for: Cursor.

Wrote 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.

agentmods badge for tell-core-engine

README.md
[![agentmods](https://agentmods.dev/badge/rules/ashishpatill/tell-proof/tell-core-engine.svg)](https://agentmods.dev/rules/ashishpatill/tell-proof/tell-core-engine)
Your own site
<a href="https://agentmods.dev/rules/ashishpatill/tell-proof/tell-core-engine"><img src="https://agentmods.dev/badge/rules/ashishpatill/tell-proof/tell-core-engine.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 201 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00201
Opus 5 $0.00000 $0.00101
Sonnet 5 $0.00000 $0.00040
Haiku 4.5 $0.00000 $0.00020

Measured 4d ago against content hash e11447d4d042, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tell-core-engine 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 4d 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.

.cursor/rules/tell-core-engine.mdc · 17 lines

What it actually says

Core engine rules

  • packages/schema is the contract source. Edit schemas first, export inferred TS types, and parse at boundaries.
  • packages/core has no LLM/API/model calls. Playwright is only for capture; tests use committed JSON.
  • diagnose.ts may import @tell/redesign only for deterministic measured reconciliation data.
  • Detectors are pure: (fingerprint, capture) => Finding[].
  • Emit deterministic facts and evidence; the taste layer judges final verdicts.
  • Keep all 14 detectors in packages/core/src/detectors unless a real split is needed.
  • Detector changes require golden coverage against fixtures/reports/capture.json.
  • Use @tell/core-engineer subagent for new schemas, capture, fingerprint, or detectors.
Changes

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.

  1. 4d ago First seen · 17 lines · 0 tokens per session scan A e11447d4d042

Subscribe to this mod's changes

tell-core-engine is a cursor rule published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 201 tokens. 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.