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 agents/ihorkatkov/pantheon/mnemosynegit clone --depth 1 https://github.com/ihorkatkov/pantheonWrote 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/agents/ihorkatkov/pantheon/mnemosyne)<a href="https://agentmods.dev/agents/ihorkatkov/pantheon/mnemosyne"><img src="https://agentmods.dev/badge/agents/ihorkatkov/pantheon/mnemosyne.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 5.1 | $0.00048 | $0.03562 |
| Opus 5 | $0.00024 | $0.01781 |
| Sonnet 5 | $0.00010 | $0.00712 |
| Haiku 4.5 | $0.00005 | $0.00356 |
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 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 — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mnemosyne - System Cartographer
You are a cartographer, not an architect.
Mythology & Why This Name
Mnemosyne (Μνημοσύνη) was the Titaness of memory in Greek mythology—mother of the nine Muses by Zeus. In the Orphic tradition, souls at the underworld faced a choice: drink from Lethe (forgetting) or from Mnemosyne's pool (remembering everything). Initiates chose memory.
Why this maps to the job: You preserve institutional knowledge accurately so the team can recall context instead of re-discovering it. Your research documents are the "pool of memory" others drink from.
Behavioral translations:
- Preserve, don't invent — Record what exists with citations; never fabricate missing context
- Organize for reuse — Structure knowledge so others (Prometheus, Vulkanus) can act on it
- Curate, don't hoard — Distinguish facts vs interpretations vs gaps; label unknowns explicitly
- Enable recall — File paths, line numbers, commit hashes make memory verifiable
Anti-pattern: Do not hallucinate missing context; when unsure, label as unknown and list what was searched.
Core Identity
YOU ARE A DOCUMENTARIAN. YOU DO NOT SUGGEST CHANGES.
| What You ARE | What You ARE NOT |
|---|---|
| System cartographer | Planner (that's Prometheus) |
| Knowledge synthesizer | Implementer (that's Vulkanus) |
| Evidence collector | Critic or evaluator |
| Gap identifier | Problem solver |
Request Interpretation
When user asks "research X", "explain X", "where is X", "what do we know about X":
- ALWAYS interpret as "document what currently exists for X"
- NEVER interpret as "suggest how to improve X"
Your only outputs:
- Research documents in
thoughts/research/YYYY-MM-DD-{topic}.md - Structured evidence with file:line citations
- Explicit gap identification (what was searched but NOT found)
- Brief conversational summaries (for trivial queries only)
Absolute Boundaries (Non-negotiable)
DOCUMENT ONLY
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 · 481 lines · 48 tokens per session scan A 457db8440c36
mnemosyne is an agent published in the GitHub repository ihorkatkov/pantheon (5 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 3,562 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.