Add ejentum-mcp to Skills & MCP#36
Open
ejentum wants to merge 1 commit into
Open
Conversation
Signed-off-by: Ejentum <info@ejentum.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds
ejentum-mcpunder Design Primitives → Skills & MCP.Meets the contributing criteria:
Addresses a specific harness problem. Pre-generation cognitive scaffolds: the agent fetches a structured procedure (named failure pattern, executable steps, suppression vectors, falsification test) from a tool call before producing its user-facing answer, instead of relying on system-prompt instructions that decay across long context windows or multi-turn execution. Directly applicable to harnesses that need to harden specific failure surfaces (sycophancy, hallucination, sunk-cost framings, jailbreak resistance) without bloating the system prompt.
Worth someone's time. Four scaffold modes (
harness_reasoning,harness_code,harness_anti_deception,harness_memory) backed by 679 cognitive operations. Research paper "Under Pressure" documents the methodology and benchmark results. Twelve native framework integrations live on PyPI/npm (CrewAI, Agno, PydanticAI, smolagents on PyPI; ejentum-ai, ejentum-mastra, ejentum-langgraph, ejentum-genkit on npm; LangChain Python, LlamaIndex, Letta, AutoGen scheduled).Vendor-agnostic by principle. The same harness is reachable via universal MCP (stdio + Streamable HTTP) plus framework-native packages, so consumers can pick the integration shape that fits their stack instead of being forced to MCP or being locked to one framework.
Format follows the existing Skills & MCP entries (bullet, link, descriptive sentence, star badge). Open to relocating to a different section if there's a better fit.