project-memory

project-memory is a skill for Claude Code, Codex from wallneradam/project-mem-mcp. It costs 297 tokens per session (2,046 once invoked), scanned A, original, MIT.

A project memory system that keeps shared technical knowledge in a MEMORY.md file. It stores information about code, architecture, conventions, and lessons from recent coding sessions.

In plain words
What is it for?
Use it to record how the codebase works, rules the project follows, known problems, and recent development context.
Why use it?
It reduces repeated explanations and helps agents remember important project details between conversations.

Skill for Claude CodeCodex

Part of the project-mem plugin — 2 skills, 1 command, 1 agent, 4 hooks shipped together

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 skills/wallneradam/project-mem-mcp/project-memory
Any agent
npx skills add wallneradam/project-mem-mcp --skill project-memory
Clone the repo
git clone --depth 1 https://github.com/wallneradam/project-mem-mcp

Made for: Claude Code, Codex.

Or install project-mem, the plugin that ships this one along with the rest of its 2 skills, 1 command, 1 agent, 4 hooks.

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 project-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/wallneradam/project-mem-mcp/project-memory.svg)](https://agentmods.dev/skills/wallneradam/project-mem-mcp/project-memory)
Your own site
<a href="https://agentmods.dev/skills/wallneradam/project-mem-mcp/project-memory"><img src="https://agentmods.dev/badge/skills/wallneradam/project-mem-mcp/project-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 297 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,046 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 $0.00297 $0.02046
Opus 5 $0.00148 $0.01023
Sonnet 5 $0.00059 $0.00409
Haiku 4.5 $0.00030 $0.00205

Measured 5d ago against content hash 0c125e07bf14, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-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 5d 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.

plugin/skills/project-memory/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Memory — Persistent Project Knowledge

You have access to a project memory system that persists knowledge between conversations via a MEMORY.md file in the project directory.

The project memory is automatically loaded at the start of each session (via hook). Your job is to keep it up to date as you work.

Scope — Project Memory vs. Auto Memory

This skill manages project memory — a single MEMORY.md file in the project directory that stores shared, code-level knowledge (architecture, conventions, gotchas). It is distinct from auto memory, Claude Code's built-in per-user memory under ~/.claude/projects/<hash>/memory/, which stores personal context about the user and their collaboration preferences.

Aspect Project memory Auto memory
Location <project>/MEMORY.md ~/.claude/projects/<hash>/memory/
Scope Shared (team, any agent) Private (per user, per working directory)
Content Code/architecture/conventions User profile, feedback, session state
Language English only Conversation language

Rule of thumb: if it describes the code, it belongs here. If it describes the user or how to collaborate with them, it belongs to auto memory. Never duplicate between the two systems; at most keep a one-line pointer in auto memory referencing the project memory.

Default to Save

Under-saving silently starves future sessions of context — that is the real risk, not over-saving. The dream protocol consolidates excess later. When in doubt, save.

Agents frequently under-save because nothing feels "important enough" in isolation; resist that instinct. If the insight took you any effort to reach (debugging, reading docs, trial and error), a future agent will want it too. Err on the side of writing one short bullet rather than nothing.

Read the full file on GitHub · 185 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. 5d ago First seen · 185 lines · 297 tokens per session scan A 0c125e07bf14

Subscribe to this mod's changes

project-memory is a skill published in the GitHub repository wallneradam/project-mem-mcp (2 stars, last pushed 17d ago), licensed MIT. It adds 297 tokens to every session and 2,046 once invoked, about $0.0015 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 skills, from other repositories

memory-bank

Token-efficient persistent memory system for Claude Code that saves 67% tokens on session warm-up (verified with tiktoken). Layered architecture with progressive loading, compact encoding, branch-aware context, smart compression, session diffing, conflict detection, session continuation protocol, and recovery mode.…

josiahcrackle9631/memory-bank · 199 tokens

claude-bridge-role-memory-keeper

Playbook for a Claude Code agent in the dedicated memory keeper role — single-writer for shared agent memory across a team of 3+ peers. Use when you are designated as the keeper (= other peers send you write candidates, you write them and watch for drift). Memory hygiene + reconciliation against the canon + drift…

michalekz/claude-bridge · 102 tokens

memai-maintenance

Orchestrator of the MemAI MAINTENANCE pass (long-term agent memory). Runs [[memai-checkpoints]], [[memai-distill]], [[memai-confidence]] and [[memai-link]] as one curation pass, owns what none of them covers — the DOMAIN TREE (nested paths, cross-listing, casing), the DIAGRAMS and the store's DECAY (reviewafter) — and…

Filipe-Soares-de-Almeida/MemAI · 184 tokens

memai-confidence

Verify a MemAI memory's claims against live facts and set its confidence (unverified | confirmed | contradicted). Checks the anchors a scan already extracted — file:line, symbol, table/column, domain, URL — against today's source, promotes or demotes each memory, stages a reword for a detail that drifted, and pushes…

Filipe-Soares-de-Almeida/MemAI · 155 tokens

memai-checkpoints

The lifecycle of MemAI CHECKPOINTS: deciding which bearing is still current and which one is superseded, archiving the checkpoint of work that is closed or an intra-session trail that a newer one already covers, keeping the single bearing a live effort still needs, correcting a fact in a kept checkpoint that has gone…

Filipe-Soares-de-Almeida/MemAI · 162 tokens

memai-distill

Distill and MOVE knowledge between MemAI types: pull what is durable out of one checkpoint (or several) into a note/reasoning/antipattern, change a memory's type (checkpoint→note when the content is timeless), and merge near-duplicates. Use when the user asks to "distill memory", "turn a checkpoint into a note", "move…

Filipe-Soares-de-Almeida/MemAI · 141 tokens