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.
npx agentmods add skills/wallneradam/project-mem-mcp/project-memorynpx skills add wallneradam/project-mem-mcp --skill project-memorygit clone --depth 1 https://github.com/wallneradam/project-mem-mcpWrote 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.
[](https://agentmods.dev/skills/wallneradam/project-mem-mcp/project-memory)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- 5d ago First seen · 185 lines · 297 tokens per session scan A 0c125e07bf14
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.
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.…
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…
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…
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…
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…
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…