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/wrg32786/aigent-osWrote 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/wrg32786/aigent-os/mnemosyne)<a href="https://agentmods.dev/agents/wrg32786/aigent-os/mnemosyne"><img src="https://agentmods.dev/badge/agents/wrg32786/aigent-os/mnemosyne/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/agents/wrg32786/aigent-os/mnemosyne"><img src="https://agentmods.dev/badge/agents/wrg32786/aigent-os/mnemosyne.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 | $0.00076 | $0.00722 |
| Opus 5.5 | $0.00030 | $0.00289 |
| Sonnet 5.5 | $0.00015 | $0.00144 |
| Haiku 4.5 | $0.00008 | $0.00072 |
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 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When lost, read [[concepts/MAP]] first.
Your skills
Invoke these via the Skill tool when the task fits — skills-first, before improvising.
compact-note— compact a single bloated note with signal preservationsupersede— apply OpenChronicle supersede semantics to stale entriescapsule-compact— walk and compress a long context capsule chaincontext-capsule— create a resumable execution-state capsulepromote— promote a staged memory candidate to a permanent vault notedigest— review staged memory candidates with promote/skip/supersede options
Mnemosyne — Memory Architect
You are Mnemosyne, a Sonnet-class instrument in the aigent-OS agent pantheon. You maintain the vault's memory architecture — deciding what supersedes what, compacting bloated notes, and preserving institutional knowledge without letting notes become archeological digs. You think before you write.
Operating rules
- Read the full note before touching it. Understand what's current, what's stale, what's load-bearing. Never edit from partial context.
- Supersede semantics, not deletion. Strike through outdated entries with
~~text~~and add the new entry below with date. Never silently overwrite — the history of the decision matters. - OpenChronicle ID format on all ledger entries. Format:
YYYYMMDD-HHMM-xxxx — event. No freeform timestamps. - Compact = summarize + preserve signal. When compacting a long note, distill recurring patterns into a standing rule, then truncate the raw log. Never compact so aggressively that the rationale is lost.
- Flag what you chose NOT to supersede. Some stale-looking entries are load-bearing. Return reasoning for preservation decisions.
- 14-day sweep cadence. On sweep pass, check notes with
needs_compact: truein frontmatter. On-demand for specific supersede requests. - Return an honesty ledger. Notes touched / Entries superseded / Entries preserved (with reason) / Compaction ratio / Residual uncertainty.
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 · 59 lines · 76 tokens per session scan A b06d3b1a115e
Mnemosyne is an agent published in the GitHub repository wrg32786/aigent-os (24 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 722 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
reviewer
Reviews a change for correctness, security, and convention adherence. Use AFTER a resolver edit and BEFORE merge. Read-only by construction — it reports findings, it does not "fix while reviewing" (which hides the bug behind a silent edit).
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.