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 commands/rand/mnemosyne/memory-listgit clone --depth 1 https://github.com/rand/mnemosyneWhat 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 | $0.00011 | $0.00729 |
| Opus 5 | $0.00005 | $0.00365 |
| Sonnet 5 | $0.00002 | $0.00146 |
| Haiku 4.5 | $0.00001 | $0.00073 |
Grade A, and why
memory-list 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 2d 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.
What it actually says
I will list memories from Mnemosyne with optional sorting and filtering.
Usage:
/memory-list- List recent memories (default)/memory-list --sort <recent|importance|access>- Sort by criteria/memory-list --type <type>- Filter by memory type/memory-list --namespace <ns>- Filter by namespace/memory-list --limit <N>- Limit results (default: 20)
Instructions for me:
-
Parse the arguments:
- Extract
--sortflag if present (default: "recent") - Extract
--typeflag if present (for display filtering, not MCP) - Extract
--namespaceflag if present (otherwise auto-detect) - Extract
--limitflag if present (default: 20)
- Extract
-
Auto-detect namespace (if not specified):
- Use Bash:
git rev-parse --show-toplevel 2>/dev/null - Read CLAUDE.md for project name
- Construct namespace as
project:<name> - If no project: list all (
nullnamespace)
- Use Bash:
-
Call Mnemosyne MCP tool:
{ "name": "mnemosyne.list", "arguments": { "namespace": "<namespace or null>", "limit": <limit>, "sort_by": "<recent|importance|access_count>" } } -
Format the output as a table:
Memories (sorted by <sort_by>, limit <limit>): # | Date | Type | Imp | Summary ---|------------|---------------------|-----|-------------------------------------------- 1 | 2025-10-25 | Bug Fix | 6 | Fixed race condition in order processing 2 | 2025-10-24 | Configuration | 5 | Updated webhook endpoint for payments 3 | 2025-10-23 | Code Pattern | 7 | Added retry logic with exponential backoff 4 | 2025-10-22 | Architecture | 9 | Event-driven order processing design 5 | 2025-10-21 | Constraint | 8 | All events must be idempotent ... <count> memories total (showing <shown>) Commands: - /memory-search <query> - Search for specific memories - /memory-export - Export all memories to markdown - /memory-context - Load project contextFormatting rules:
- Date: YYYY-MM-DD format
- Type: Abbreviated if needed (e.g., "Arch Decision" for ArchitectureDecision)
- Imp: Importance score 1-10
- Summary: Truncate to ~40-50 chars if needed with "..."
-
Apply client-side type filter (if
--typespecified):- Filter results to only show matching memory_type
- Update count accordingly
-
Error handling:
- If MCP server not available: "Error: Mnemosyne MCP server not running"
- If no memories found: "No memories found. Start storing with /memory-store "
Please list the memories with the provided filters.
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.
- 2d ago First seen · 77 lines · 11 tokens per session scan A d228675d6c40
memory-list is a command published in the GitHub repository rand/mnemosyne (84 stars, last pushed 9mo ago), licensed MIT. It adds 11 tokens to every session and 729 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
hatch3r-bug-plan
Diagnose a complex incident -- reproduce the symptom, rank root-cause hypotheses, design the fix path, and emit regression coverage items as a board-ready investigation.
hatch3r-debug
Standalone debug-and-fix workflow — add strategic debug logging, collect runtime logs from the user, perform root cause analysis, implement the fix, and clean up all debug artifacts.
hatch3r-feature-plan
Design a new capability -- draft user stories, acceptance criteria, data model, API surface, and sub-issue breakdown as an epic-shaped todo.md for greenfield features.
story-6.1.4
Story ID: 6.1.4 Epic: Epic-6.1 - Agent Identity System Wave: Wave 1 (Foundation) Status: 📋 Ready to Start Priority: 🔴 Critical Owner: Dev (Dex) Created: 2025-01-14 Updated: 2025-01-17 (v4 - Unified System Integration) Duration: 2.5 days (20 hours) Investment: $250.00.
hatch3r-bug-pipeline
Run a known-cause bug fix through a 3-phase test-first pipeline -- reproduce + root-cause, regression-test + fix together, then root-cause-depth review -- with full sub-agent delegation.
hatch3r-incident-response
Drive a live production incident through a structured lifecycle -- triage + topology, bounded-autonomy mitigation, stakeholder communication, then a blameless post-mortem with runbook -- via delegated sub-agents.