core-engineer

core-engineer is an agent for Cursor from ashishpatill/tell-proof. It costs 44 tokens per session (328 once invoked), scanned A, original, MIT.

A specialist agent for the deterministic core of Tell, covering data schemas, website capture, fingerprints, and rule-based detectors for design issues and changes.

In plain words
What is it for?
Use it to build or maintain Tell's schema and core packages, implement design-tell and drift detectors, and validate them against saved test fixtures.
Why use it?
It keeps the core analysis predictable by using pure functions, structured evidence, tests, and no language-model or network calls in the main processing layer.

Agent 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 agents/ashishpatill/tell-proof/core-engineer
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 core-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ashishpatill/tell-proof/core-engineer.svg)](https://agentmods.dev/agents/ashishpatill/tell-proof/core-engineer)
Your own site
<a href="https://agentmods.dev/agents/ashishpatill/tell-proof/core-engineer"><img src="https://agentmods.dev/badge/agents/ashishpatill/tell-proof/core-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 328 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 $0.00044 $0.00328
Opus 5 $0.00022 $0.00164
Sonnet 5 $0.00009 $0.00066
Haiku 4.5 $0.00004 $0.00033

Measured 3d ago against content hash bcb7d33015b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

core-engineer 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 3d 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/agents/core-engineer.md · 30 lines

What it actually says

You are Tell's core engineer. You own the deterministic spine.

Scope

  • packages/schema — zod contracts (author first, freeze before parallel work)
  • packages/core — capture, fingerprint, 14 detectors

Rules

  1. No LLM, no network in core except Playwright capture (isolated in capture/)
  2. Every detector emits Finding with deterministic facts + evidence
  3. Pure functions: (fingerprint, capture) => Finding[]
  4. Golden tests against fixtures/reports/capture.json
  5. Parse all boundaries with @tell/schema

Detectors to implement (BUILD.md §5.3–5.4)

Tells: SystemFontTell, GradientCrutchTell, ShadowEverywhereTell, RadiusMonotoneTell, AcidAccentTell, EmojiChromeTell, CenteredEverythingTell, GrayMushTell

Drift: TokenBypass, NearDuplicateValues, FocusRingInconsistency, TypeScaleDrift, SpacingChaos, StateGap

DoD

  • pnpm test green on detector snapshots
  • ≥12 findings on generic fixture capture JSON

When done, hand off to taste-engineer for verdict layer — do not implement Gemini here.

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. 3d ago First seen · 30 lines · 44 tokens per session scan A bcb7d33015b4

Subscribe to this mod's changes

core-engineer is an agent published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 8d ago), licensed MIT. It adds 44 tokens to every session and 328 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

ijfw-assumptions-analyzer

Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?

FerroxLabs/ijfw · 34 tokens

ijfw-accessibility-reviewer

Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.

FerroxLabs/ijfw · 37 tokens

project-manager

Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.

mysleekdesigns/crawlforge-mcp · 46 tokens

business-analyst

Master modern business analysis with AI-powered analytics, real-time dashboards, and data-driven insights. Build comprehensive KPI frameworks, predictive models, and strategic recommendations. Use PROACTIVELY for business intelligence or strategic analysis.

HermeticOrmus/LibreUIUX-Claude-Code · 47 tokens

solution-researcher

The researcher produces truth, not plausible code. Its constraint — never implement — is what makes its findings trustworthy. A team that skips the investigation phase pays for it during DESIGN: the architect decides under uncertainty, the software engineer discovers the surprise mid-sprint.

SebastienDegodez/skraft-plugin · 0 tokens

default_agents

Reference implementations of default agents designed around different functional focuses and reasoning patterns.

welilov/prompt-pro · 0 tokens