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/wrg32786/aigent-os/mnemosynegit 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.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 | $0.00076 | $0.00722 |
| Opus 5 | $0.00038 | $0.00361 |
| Sonnet 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 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.
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.
- 2d ago First seen · 59 lines · 76 tokens per session scan A b06d3b1a115e
Mnemosyne is an agent published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 722 once invoked, about $0.0004 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 2026-09-03.
Other agents, from other repositories
universal
Paste this into your agent/LLM system instruction block.
hermes-agent
Runtime.
Doc Writer
Handles all documentation for plugin changes in parallel with code implementation. Updates README, READMECN, docs mirrors, and standalone version files.
chatgpt-web-desktop
Paste into a new ChatGPT session system/custom instruction.
claude-web-desktop
Paste into a new Claude session instruction.
mercury-agent
Runtime.