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.
git clone --depth 1 https://github.com/tm42/mnemographWrote 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/commands/tm42/mnemograph/visualize-memory-graph)<a href="https://agentmods.dev/commands/tm42/mnemograph/visualize-memory-graph"><img src="https://agentmods.dev/badge/commands/tm42/mnemograph/visualize-memory-graph/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/tm42/mnemograph/visualize-memory-graph"><img src="https://agentmods.dev/badge/commands/tm42/mnemograph/visualize-memory-graph.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00013 | $0.00542 |
| Opus 5.5 | $0.00005 | $0.00217 |
| Sonnet 5.5 | $0.00003 | $0.00108 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade A, and why
visualize-memory-graph 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 1mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visualize Memory Graph
Open an interactive D3.js visualization of the knowledge graph in the browser.
Your Task
Before running the visualization, ask the user which memory scope and mode they want using the AskUserQuestion tool.
Instructions
-
Ask the user for their preferences using AskUserQuestion with these questions:
Question 1 - Memory Scope:
- Header: "Scope"
- Question: "Which memory graph do you want to visualize?"
- Options:
- Label: "Global memory", Description: "Your personal knowledge graph stored in ~/.claude/memory (shared across all projects)"
- Label: "Project memory", Description: "Project-specific knowledge graph stored in .claude/memory (local to this codebase)"
Question 2 - Mode:
- Header: "Mode"
- Question: "How do you want to view the graph?"
- Options:
- Label: "Live view (Recommended)", Description: "Opens in browser with a Refresh button for live updates as you work"
- Label: "Export only", Description: "Save the graph as an HTML file without opening the browser"
-
Run the visualization based on their choices:
Use the Bash tool to run the
mnemograph graphcommand viauvx.Commands by choice combination:
Scope Mode Command Global Live uvx mnemograph --global graph --watchGlobal Export uvx mnemograph --global graph --export ~/mnemograph-export.htmlProject Live uvx mnemograph graph --watchProject Export uvx mnemograph graph --export ./mnemograph-export.htmlRun in background for live view mode so the user can continue working while the server runs.
-
Inform the user about what's happening:
- For live view: Tell them the server is running and they can click Refresh in the browser
- For export: Tell them where the file was saved
Notes
- The live view runs a local HTTP server — tell the user to press Ctrl+C or click "Stop Server" in the browser when done
- The visualization shows entities as nodes and relations as edges
- Node colors represent entity types (concept, decision, pattern, etc.)
- Edge thickness represents relation weight (stronger connections = thicker lines)
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.
- 1mo ago First seen · 56 lines · 13 tokens per session scan A eb800a94127f
visualize-memory-graph is a command published in the GitHub repository tm42/mnemograph (2 stars, last pushed 8mo ago), licensed MIT. It adds 13 tokens to every session and 542 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
rb-refresh
A command that rebuilds RepoBrain's knowledge base for the current workspace. RepoBrain is a tool that keeps searchable project information for an agent.
ingest
Ingest source material into an active wiki. Accepts URLs, file paths, PDFs, freeform text, or processes the inbox. Supports tweets via Grok MCP.
iai-directive
Record, list, or remove a standing order the user typed themselves.
init-workspace-flow-questions
Phase 8 Questions of init-workspace-flow.
memo
Search, save, inspect, and maintain memo persistent memory.
local
Command "local" from getsentry/toolkit, covering examples, start the server and tail events (default), run your app with the local server auto-enabled, use a custom port and only show errors and logs (filter out transactions).