agentmods.dev

memarium

memarium is a command for coding agents from june9593/memarium-plugin. It costs 45 tokens per session (514 once invoked), scanned A, original, MIT.

A command for turning completed work sessions into a structured project memory system. It creates records of work threads, facts, procedures, entities, and question-and-answer material.

In plain words
What is it for?
It is for reviewing synced sessions, separating them into work threads, and saving reusable project memories.
Why use it?
It helps preserve useful decisions, discoveries, dead ends, and project knowledge after a session ends.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the memarium plugin — 4 skills, 4 commands, 2 hooks shipped together

not rated 1 29d ago A scan 45 tokens original MIT
View the source file june9593/memarium-plugin
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 commands/june9593/memarium-plugin/memarium
Clone the repo
git clone --depth 1 https://github.com/june9593/memarium-plugin

Or install memarium, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 2 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 memarium

README.md
[![agentmods](https://agentmods.dev/badge/commands/june9593/memarium-plugin/memarium.svg)](https://agentmods.dev/commands/june9593/memarium-plugin/memarium)
Your own site
<a href="https://agentmods.dev/commands/june9593/memarium-plugin/memarium"><img src="https://agentmods.dev/badge/commands/june9593/memarium-plugin/memarium.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 514 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 $0.00045 $0.00514
Opus 5 $0.00023 $0.00257
Sonnet 5 $0.00009 $0.00103
Haiku 4.5 $0.00005 $0.00051

Measured 3d ago against content hash 8e4a04f6e2b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memarium 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 3d 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.

commands/memarium.md · 26 lines

What it actually says

Invoke the memarium skill via the Skill tool with skill: "memarium:memarium".

The skill walks you through (typed-memory only — there is no book/chronicles/topics):

  1. Locate the plugin binary (VBP="${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT/bin/memarium-plugin.js}"; [ -x "$VBP" ] || VBP=$(ls -d ~/.claude/plugins/cache/*/memarium/*/bin/memarium-plugin.js | awk -F/ '{print $(NF-2)"\t"$0}' | sort -V | tail -1 | cut -f2-)).
  2. Run "$VBP" orchestrate project --cwd "$(pwd)" to prime the spool and detect mode.
  3. Run "$VBP" prepare --cwd "$(pwd)" to discover un-digested sessions (those not referenced by an episodic memory and not skip-ledgered).
  4. For 0.7+ manifest_version: 1 source md, navigate via the embedded manifest + Table of Contents instead of loading the whole body (P3 chunked reading).
  5. Segment sessions into threads (one episodic per thread).
  6. Write an episodic {entry, body} per non-skip thread (references/episodic-format.md: Context / What worked / Dead ends / Open questions / Decisions; sourceSessions correct; work-status in the body, NOT entry.status), plus distilled semantic/procedural/core facts, the entity wiki, and Q&A.
  7. Persist via "$VBP" memory-write (non-gated: episodic/plain-semantic) and "$VBP" memory-propose (gated: core/procedural/pinned/supersede/trust-elevation); surface proposals for review.
  8. Record skipped sessions with "$VBP" skip-write, then "$VBP" finalize to commit + push.

Per-project isolation is a hard rule. This is the batch digest; /memarium-retro is its lightweight in-session counterpart (capture one insight live).

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. 3d ago First seen · 26 lines · 45 tokens per session scan A 8e4a04f6e2b0

Subscribe to this mod's changes

memarium is a command published in the GitHub repository june9593/memarium-plugin (1 stars, last pushed 29d ago), licensed MIT. It adds 45 tokens to every session and 514 once invoked, about $0.0002 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.

Memory and contextai-agentsclaude-codeclaude-code-plugindeveloper-tools
Related

Other commands, from other repositories

learn

Force claude-smart to extract learnings from this session now.

ReflexioAI/claude-smart · 14 tokens

recall-save

Generate / overwrite .recall/context.md with Recall's local offline summarizer.

raiyanyahya/recall · 15 tokens

show

Show this project's saved Recall context (.recall/context.md).

raiyanyahya/recall · 12 tokens

coding-drill

Rapid-fire reps — pattern recognition, complexity-of-this-snippet, template recall — flashcard cadence; prioritizes your weak patterns.

kirilxd/swe-interview-coach · 26 tokens

init

Bootstrap project context (project.intent.md and project.glossary.json) from an existing codebase using deterministic scan + LLM synthesis + interactive editing. Use --harness to scaffold additional repo-level harness docs.

heurema/signum · 44 tokens

ai-act-ask

Answer an EU AI Act question grounded in the bundled knowledge base — verbatim statute text, obligation paraphrases, and the compound-risk taxonomy. Offline and deterministic by default; cites the articles it relies on.

Peaky8linders/eu-ai-act-scanner · 46 tokens