memophant

memophant is a cursor rule for Cursor from awizemann/harness. It costs 588 tokens per session, scanned A, a copy of memophant, MIT.

A set of project rules for using Memophant as the source of truth for durable project memory. It covers searching, editing, storing credentials, and keeping managed memory files out of ordinary Git commits.

In plain words
What is it for?
Use it to search and update memory, record decisions, store vendor credentials safely, and handle projects where Memophant tools are unavailable by searching its local files.
Why use it?
It reduces duplicated notes, protects secrets, and keeps project decisions in the memory system where later sessions can find them.

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/awizemann/harness/memophant
Clone the repo
git clone --depth 1 https://github.com/awizemann/harness

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 memophant

README.md
[![agentmods](https://agentmods.dev/badge/rules/awizemann/harness/memophant.svg)](https://agentmods.dev/rules/awizemann/harness/memophant)
Your own site
<a href="https://agentmods.dev/rules/awizemann/harness/memophant"><img src="https://agentmods.dev/badge/rules/awizemann/harness/memophant.svg" alt="Measured on agentmods" height="20"></a>
Per session 588 This file is loaded in full into every session.
When invoked 588 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00588 $0.00588
Opus 5 $0.00294 $0.00294
Sonnet 5 $0.00118 $0.00118
Haiku 4.5 $0.00059 $0.00059

Measured yesterday against content hash 53def41403bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memophant 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 yesterday.

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.

Origin

This is a copy

100% identical to memophant — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/rules/memophant.mdc · 17 lines

What it actually says

Memory System (managed by Memophant) — core rules. Full reference: AGENTS.md.

  1. Memory is the source of truth. Search it before assuming; record durable decisions/learnings as memory notes or wiki pages — never in this file or session-private/model memory. Search before writing and edit an existing note (edit_memory) rather than forking a near-duplicate.
  2. Prefer the memophant MCP tools for every read/write (search/read/write/edit/move) — read each tool's description (they document their args). The engine is the gate: the tool/app entry points carry the guards (slug-gen, structure validation, write-time secret scan); direct edits reconcile automatically but skip them — never compose your own guard set. Tools absent → grep the MAIN CHECKOUT's .memory/ + wiki/; a git worktree's copy of those tiers is a base-commit snapshot and is stale by construction, so never grep ./ from one.
  3. Don't git add/commit the managed tiers (.memory/, wiki/, design/, code/, sessions/, documents/, vendors/, templates/, TASKS.md, tasks/) — the user commits each via Memophant's per-tier secret-scanned bar; leave them dirty. Everything else is yours.
  4. Secrets → Keychain, never chat or files. Found or made a credential? Store it with set_vendor_credential (fetch later with get_vendor_credential); never leave it loose in chat.
  5. Agent artifacts (plans/reports/briefs) → documents/ (exact lowercase), via write_tier_file(tier: "documents", path: …) — never a repo's docs/ folder (that's the project's own documentation) and never a case-variant like Documents/.
  6. Read the project charter (read_charter) at session start when this project has one (.memory/charter.md) — its commandments are absolute and OUTRANK memory notes, this file, and your brief; "No charter" is a normal answer. It's human-only: propose changes as a task tagged charter, never edit it. File memory notes under one of six folders (architecture/conventions/decisions/operations/project/roadmap), never the root. When a note is grounded in code, pass source_paths (the repo files it depends on) so Memory Health can drift-check it — an unanchored code note can't be kept current.
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. yesterday Changed · +1 lines · +110 tokens per session 53def41403bd
  2. 5d ago First seen · 16 lines · 478 tokens per session scan A 6195baa7fe13

Subscribe to this mod's changes

memophant is a cursor rule published in the GitHub repository awizemann/harness (344 stars, last pushed 2d ago), licensed MIT. It adds 588 tokens to every session, about $0.0029 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to memophant, differing in 3 lines, and is treated as a copy.