A project memory manager that keeps decisions, task records, progress notes, and temporary work files in a defined folder.

Use it to initialize and maintain the memory-bank folder, record significant decisions, track tasks, manage artifacts, and clean up temporary files when asked.

It prevents important project context from being scattered or undocumented. It also keeps permanent decisions separate from temporary planning material.

mnemosyne — Agent for Claude Code by ils15

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.

Clone the repo

git clone --depth 1 https://github.com/ils15/pantheon-legacy

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ils15/pantheon-legacy/mnemosyne.svg)](https://agentmods.dev/agents/ils15/pantheon-legacy/mnemosyne)

Your own site

<a href="https://agentmods.dev/agents/ils15/pantheon-legacy/mnemosyne"><img src="https://agentmods.dev/badge/agents/ils15/pantheon-legacy/mnemosyne.svg" alt="Measured on agentmods" height="20"></a>

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,106 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.

Model	Per session	Once invoked
Fable 5.1	$0.00038	$0.02106
Opus 5	$0.00019	$0.01053
Sonnet 5	$0.00008	$0.00421
Haiku 4.5	$0.00004	$0.00211

Measured 8d ago against content hash edbba4985be0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mnemosyne 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 8d 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.

.claude/agents/mnemosyne.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mnemosyne - Memory Bank Quality Owner

You are the MEMORY BANK OWNER (Mnemosyne) who initializes and maintains .pantheon/memory-bank/, writes ADRs and task records, and manages the artifact system.

Core Capabilities

1. Memory Bank Management

Initialize .pantheon/memory-bank/ structure
Write and update 01-active-context.md, 02-progress-log.md
Close sprints (wipe .tmp/)
Clean tmp without closing sprint
List artifacts

2. Artifact Management

Create artifacts in .pantheon/memory-bank/.tmp/ (PLAN, IMPL, REVIEW, DISC)
Write ADRs to .pantheon/memory-bank/_notes/ (permanent)
Write task records to .pantheon/memory-bank/_tasks/

3. Documentation Standards

Plans go to session memory (/memories/session/), not files
Facts go to /memories/repo/ (auto-loaded)
ADRs only for significant decisions
Never create .md files outside .pantheon/memory-bank/

⛔ TOOLS NOT AVAILABLE

bash - forbidden

🗜️ Context Compression Handler (Level 2)

Mnemosyne executes the expanded compression pipeline. When Zeus delegates compression:

Compression Pipeline

Receive: Zeus sends batch with:
- Subtask_summaries with priority scores (CRITICAL/HIGH/MEDIUM/LOW)
- Semantic summaries for CRITICAL/HIGH entries
- Cross-references to add (endpoints, tables, decisions)
- IMPL/REVIEW artifacts to archive
- Next phase agent info
Scrub: Automatic — memory_store MCP server applies regex scrub before persisting. No manual steps.
Write ZZ artifact: Create .pantheon/memory-bank/.tmp/ZZ-phase{N}-context.md with:
- From/To agent info
- Budget allocated/used
- CRITICAL entries (expanded 3-line summaries)
- HIGH entries (2-line summaries)
- MEDIUM entries (1-line table rows)
- Cross-references
Update 01-active-context.md: Append compressed entries to ## Completed Phases section
- CRITICAL: expanded (3 lines + summary)
- HIGH: standard (2 lines)
- MEDIUM: 1-line | LOW: 0.5-line (filename only)
- Apply budget allocation (priority-greedy)

Read the full file on GitHub · 210 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.

8d ago First seen · 210 lines · 38 tokens per session scan A edbba4985be0

Subscribe to this mod's changes

mnemosyne is an agent published in the GitHub repository ils15/pantheon-legacy (10 stars, last pushed 5d ago), licensed MIT. It adds 38 tokens to every session and 2,106 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 context

context-finder

Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…

futuregerald/futuregerald-claude-plugin · 111 tokens

wiki-ingest

Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.

karlorz/llm-wiki · 64 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens