mhn-ai-agent-memory: Skill for Cursor

.cursor/skills/mhn-project-working-memory/SKILL.md

mhn-project-working-memory is a skill for Cursor from shahzebqazi/mhn-ai-agent-memory. It costs 64 tokens per session (682 once invoked), scanned A, original, MIT.

A shared project memory system that saves facts and notes in a JSON file inside the project. It uses associative search so different Cursor agents and sessions can find and reuse the stored context.

In plain words
What is it for?
Use it to save project facts, maintain working memory, build a local knowledge base, and hand work from one agent or session to another.
Why use it?
It prevents agents from losing project knowledge between sessions or requiring the same background to be explained again.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is shahzebqazi/mhn-ai-agent-memory's own configuration. It tells Cursor how to work on mhn-ai-agent-memory itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mhn-ai-agent-memory configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shahzebqazi/mhn-ai-agent-memory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/shahzebqazi/mhn-ai-agent-memory/main/.cursor/skills/mhn-project-working-memory/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/shahzebqazi/mhn-ai-agent-memory

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 mhn-project-working-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/shahzebqazi/mhn-ai-agent-memory/mhn-project-working-memory/github.svg)](https://agentmods.dev/skills/shahzebqazi/mhn-ai-agent-memory/mhn-project-working-memory)
Your own site
<a href="https://agentmods.dev/skills/shahzebqazi/mhn-ai-agent-memory/mhn-project-working-memory"><img src="https://agentmods.dev/badge/skills/shahzebqazi/mhn-ai-agent-memory/mhn-project-working-memory/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mhn-project-working-memory

Your own site · 80×15
<a href="https://agentmods.dev/skills/shahzebqazi/mhn-ai-agent-memory/mhn-project-working-memory"><img src="https://agentmods.dev/badge/skills/shahzebqazi/mhn-ai-agent-memory/mhn-project-working-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 682 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00064 $0.00682
Opus 5 $0.00032 $0.00341
Sonnet 5 $0.00013 $0.00136
Haiku 4.5 $0.00006 $0.00068

Measured 12d ago against content hash 22bbc1ec7248, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mhn-project-working-memory 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 12d 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/skills/mhn-project-working-memory/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MHN project working memory (Cursor)

Idea

Associative memory lives in a JSON file on disk (not in chat). Any agent with the same MCP config reads and updates the same store, so memory is swappable between agents and survives new conversations.

Setup (once per machine)

  1. Create the MCP server venv: see mcp-server/README.md (pip install -e . inside mcp-server/).
  2. Copy .cursor/mcp.json.example to .cursor/mcp.json in this repo (or merge the hopfield-memory entry into user-level MCP config).
  3. Replace placeholder paths with absolute paths to mcp-server/.venv/bin/python and mcp-server/server.py, or use ${workspaceFolder} if your Cursor build expands it.
  4. Set HOPFIELD_STATE_PATH to a path inside the project (default example: .mhn/working-memory.json). Enable HOPFIELD_AUTO_SAVE=true so store / store_negative persist immediately.
  5. Restart MCP / Cursor so the server picks up env vars.

The bundled .cursor/mcp.json.example sets HOPFIELD_ENCODER to sentence_transformer; install the parent package with semantic extras into the same venv as the MCP server (./mcp-server/.venv/bin/pip install -e ".[semantic]" from repo root), or change that env var to random if you want no extra dependencies (weaker recall).

Use sentence_transformer (or better encoders) for semantic recall; random is fine only for exact-token overlap demos.

Agent workflow

  1. working_memory_status — Confirm state_path, auto_save, and num_facts before relying on memory.
  2. list_facts — Treat as a cheap “table scan” of the local knowledge base (all stored strings).
  3. retrieve — Ranked facts with weights for a cue (like a fuzzy DB query).
  4. query_or_none — Prefer when the agent must distinguish “found in memory” vs “nothing relevant” (set min_similarity if needed).
  5. store — Persist decisions, constraints, file paths, API shapes, user prefs, open questions. Keep facts short and atomic when possible.
  6. save / load — Optional explicit snapshots to other paths (e.g. backup or experiment branch).

Read the full file on GitHub · 38 lines

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. 12d ago First seen · 38 lines · 64 tokens per session scan A 22bbc1ec7248

Subscribe to this mod's changes

mhn-project-working-memory is a skill published in the GitHub repository shahzebqazi/mhn-ai-agent-memory (5 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 682 once invoked, about $0.0003 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.