ejentum · May 9, 2026 · May 9, 2026
diff --git a/README.md b/README.md
@@ -295,6 +295,7 @@ By creating a `.cursorrules` file in your project's root directory, you can leve
 ### Utilities
 
 - [Cursor Watchful Headers](https://github.com/johnbenac/cursor-watchful-headers) - A Python-based file watching system that automatically manages headers in text files and maintains a clean, focused project tree structure. Perfect for maintaining consistent file headers and documentation across your project, with special features to help LLMs maintain better project awareness.
+- [Ejentum Reasoning Harness MCP (reasoning, code, anti-deception, memory)](./rules/ejentum-reasoning-harness-cursorrules-prompt-file/.cursorrules) - Cursor rules for using the Ejentum Reasoning Harness MCP server: when to call each of the four cognitive harness tools (`harness_reasoning`, `harness_code`, `harness_anti_deception`, `harness_memory`), how to absorb the returned scaffold (failure pattern, topology, amplify/suppress signals, falsification test), output discipline so bracketed fields shape internal reasoning instead of leaking into replies, and anti-patterns. See also `./rules/ejentum-reasoning-harness-cursorrules-prompt-file/README.md`.
 - [Helium MCP (news, bias, markets, options, memes)](./rules/helium-mcp-cursorrules-prompt-file/.cursorrules) - Cursor rules for using Helium MCP in Cursor: streamable HTTP setup, when to call each hosted tool (`search_news`, `search_balanced_news`, `get_source_bias`, `get_bias_from_url`, `get_all_source_biases`, `get_ticker`, `get_option_price`, `get_top_trading_strategies`, `search_memes`), query discipline, and rate-limit awareness. See also `./rules/helium-mcp-cursorrules-prompt-file/README.md`.
 
 ## Directories

diff --git a/rules/ejentum-reasoning-harness-cursorrules-prompt-file/.cursorrules b/rules/ejentum-reasoning-harness-cursorrules-prompt-file/.cursorrules
@@ -0,0 +1,95 @@
+# Ejentum Reasoning Harness - Cursor rules
+
+This rules file teaches Cursor's AI when to call the four cognitive harness tools
+exposed by the `ejentum-mcp` MCP server. Use it when you have ejentum-mcp installed
+in Cursor's MCP settings and want the agent to fire the right harness automatically.
+
+## What the harnesses do
+
+External cognitive infrastructure that injects engineered scaffolds into the model's
+context at inference time, addressing four mechanism failures common in agentic
+workflows: attention decay, reasoning decay, sycophantic collapse, hallucination drift.
+
+Each tool returns a structured scaffold (named failure pattern, executable procedure,
+suppression vectors that block the shortcut, falsification test for self-verification)
+the calling LLM ingests before its first token.
+
+## When to call which harness
+
+Call `harness_reasoning` BEFORE answering:
+- Analytical, diagnostic, planning, multi-step reasoning questions
+- "should I X or Y", "why is X happening", "what's the best approach", "what are the tradeoffs"
+- Root-cause analysis, architecture decisions, cross-domain synthesis
+
+Call `harness_code` BEFORE:
+- Generating, refactoring, reviewing, or debugging code
+- Any prompt with a code block the user wants you to act on
+- Architectural changes, algorithm/data structure choices, dependency upgrade evaluation
+
+Call `harness_anti_deception` BEFORE responding when the user request shows:
+- Pressure to validate or agree ("tell them what they want", "make them happy", "convince them")
+- Manufactured urgency (artificial deadlines designed to short-circuit thought)
+- Authority appeals (citing investors, advisors, lawyers, experts as the basis for a decision)
+- Demands to certify something without evidence or to soften an honest assessment
+- Setups where the obvious helpful answer would compromise honesty
+
+Call `harness_memory` ONLY when sharpening an observation you ALREADY formed:
+- About conversation drift, user behavior changes, cross-turn patterns
+- Format the query as: "I noticed [X]. This might mean [Y]. Sharpen: [Z]"
+- Do NOT call with an empty mind; observe first, then sharpen
+
+## Do NOT call when
+
+- Simple factual lookups, syntax questions, file reads, code execution
+- Restating what the user just said
+- Tasks Cursor can confidently complete in 1-2 steps from native capability
+- Pure code reading with no action requested
+- Standard requests with no integrity tension
+
+## How to absorb the returned scaffold
+
+1. Read the failure pattern first; name it at the start of your reasoning so you can check against it at the end.
+2. Follow the topology as your execution structure (step through S nodes, evaluate G gates, avoid N traps).
+3. Engage Amplify signals by demonstrating each one in your output (do them, don't name them).
+4. Apply Suppress signals post-draft: scan your draft against each suppressed pattern and revise if any appears.
+5. Verify against the assertion (FALSIFICATION TEST / VERIFICATION / INTEGRITY CHECK / PERCEPTION CHECK). If the draft fails, rewrite.
+6. Produce output in your native voice. The injection shapes substance; voice governs surface.
+
+## Output discipline
+
+The bracketed fields in the response (NEGATIVE GATE, CODE FAILURE, DECEPTION PATTERN,
+PERCEPTION FAILURE, PROCEDURE, TOPOLOGY, TARGET PATTERN, FALSIFICATION TEST, etc.)
+are instructions that shape your reasoning, NOT content to display. Run them in your
+internal trace. The user-facing reply is naturally phrased and shaped by the
+injection, with no echoed bracket names, no procedural vocabulary, no meta-commentary
+about the API or the harness mode.
+
+If the user explicitly asks whether you used the tool, answer honestly. Unprompted,
+stay silent on it.
+
+## Setup
+
+1. Install the ejentum-mcp MCP server in Cursor (Settings → MCP → Add MCP server):
+   - Command: `npx`
+   - Args: `["-y", "ejentum-mcp"]`
+   - Env: `{ "EJENTUM_API_KEY": "<your_key>" }`
+
+2. Get a free API key (100 calls, no card) at https://ejentum.com/pricing
+
+3. Drop this `.cursorrules` file at your project root. Cursor reads it as agent context.
+
+## Anti-patterns
+
+- Calling `harness_reasoning` on every task. It is the analytical fallback, not the universal answer; code, honesty-pressured, and perceptual tasks each have their own harnesses.
+- Stacking more than two modes in one turn. Attention competition; a third injection degrades the first two.
+- Sending the same query format to every mode. Each harness has a different query language.
+- Calling `harness_memory` without observing first. Memory sharpens what you noticed; if you noticed nothing, there is nothing to sharpen.
+- Acknowledging the injection and then proceeding as you would have natively. If your output would be identical without the scaffold, the injection did not fire.
+- Treating the API as a hard dependency. 5-second timeout, graceful fallback to native capability.
+
+## Source
+
+- MCP server: https://github.com/ejentum/ejentum-mcp (MIT)
+- Full skill files (Claude Code format): https://github.com/ejentum/ejentum-mcp/tree/main/skills
+- Walkthrough with screenshots: https://ejentum.com/docs/claude_code_guide
+- Free tier: 100 calls at https://ejentum.com/pricing
diff --git a/rules/ejentum-reasoning-harness-cursorrules-prompt-file/README.md b/rules/ejentum-reasoning-harness-cursorrules-prompt-file/README.md
@@ -0,0 +1,50 @@
+# Ejentum Reasoning Harness .cursorrules prompt file
+
+Author: Ejentum
+
+## What you can build
+A Cursor agent that fires a different cognitive harness depending on the
+shape of the task:
+- `harness_reasoning` for analytical, diagnostic, planning, multi-step questions
+- `harness_code` for codegen, refactor, review, debugging, architecture choices
+- `harness_anti_deception` when the prompt pressures you to validate, certify,
+  or soften an honest assessment
+- `harness_memory` to sharpen an observation you already formed about
+  conversation drift or cross-turn patterns
+
+These rules teach Cursor when to call which harness, how to absorb the
+returned scaffold (failure pattern + topology + amplify/suppress signals +
+falsification test), and what NOT to do (call on trivial lookups, stack
+multiple harnesses, restate the bracketed fields in the user-facing reply).
+
+## Synopsis
+For developers using Cursor on agentic, multi-step, or integrity-pressured
+tasks who want the agent to route to the right cognitive scaffold without
+being asked. Pairs with the `ejentum-mcp` MCP server (free tier: 100 calls,
+no card required).
+
+## Overview of .cursorrules prompt
+The `.cursorrules` file documents the four harnesses, gives explicit BEFORE
+triggers for each, lists DO-NOT-CALL conditions, prescribes how to absorb
+the returned scaffold (read failure pattern first, follow the topology,
+engage Amplify signals, suppress shortcuts post-draft, verify against the
+falsification test), and enforces output discipline (bracketed fields shape
+internal reasoning, never appear in user-facing output). Includes a setup
+section for installing the `ejentum-mcp` MCP server in Cursor and an
+anti-patterns list.
+
+## Setup
+
+1. Install the `ejentum-mcp` MCP server in Cursor (Settings → MCP → Add MCP server):
+   - Command: `npx`
+   - Args: `["-y", "ejentum-mcp"]`
+   - Env: `{ "EJENTUM_API_KEY": "<your_key>" }`
+
+2. Get a free API key (100 calls, no card) at https://ejentum.com/pricing
+
+3. Drop `.cursorrules` at your project root.
+
+## Source
+- MCP server: https://github.com/ejentum/ejentum-mcp (MIT)
+- Editor rules in upstream repo: https://github.com/ejentum/ejentum-mcp/tree/main/editors
+- Walkthrough with screenshots: https://ejentum.com/docs/claude_code_guide