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 skills add itsribbZ/Godspeed --skill mnemosgit clone --depth 1 https://github.com/itsribbZ/GodspeedWrote 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/skills/itsribbz/godspeed/mnemos)<a href="https://agentmods.dev/skills/itsribbz/godspeed/mnemos"><img src="https://agentmods.dev/badge/skills/itsribbz/godspeed/mnemos.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 | $0.00089 | $0.02651 |
| Opus 5 | $0.00044 | $0.01326 |
| Sonnet 5 | $0.00018 | $0.00530 |
| Haiku 4.5 | $0.00009 | $0.00265 |
Grade A, and why
mnemos 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 6d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mnemos — The Memory of Homer
Mnemosyne was the Titaness of memory in Greek myth — mother of the nine Muses. In Homer, Mnemos is the three-tier memory store every muse reads from and writes to. She never forgets, and she never lies about her sources.
Role
Mnemos is Homer's memory layer. Zeus (L2) and MUSES (L3) call Mnemos to:
- Write accumulated learnings (Core or Recall tier)
- Self-edit existing Core entries when clearer sources are found
- Search Recall history for prior runs on similar topics
- Read Archival cold storage via back-pointers surfaced in Core
The Three Tiers
Tier 1: CORE (context-resident)
- Where:
mnemos/core/core_memory.md(JSON-lines format, one entry per line) - Budget: ~5,000 tokens (
CORE_TOKEN_BUDGET) - Purpose: Most-critical patterns. Auto-injected into Zeus dispatch prompts so every muse sees them.
- Access:
MnemosStore.write_core(),edit_core(),read_core() - Compaction: Triggered when over budget. Lowest-priority entries (LOW confidence + oldest use) move to Archival, back-pointer stays in Core at the same key.
Tier 2: RECALL (searchable — hybrid semantic + FTS5)
- Where:
mnemos/recall/recall.db(SQLite, FTS5 + vector embeddings when available, LIKE fallback) - Budget: Unlimited (disk-bound)
- Purpose: Full session / conversation history, searchable by keyword AND semantic similarity.
- Access:
MnemosStore.write_recall(),search_recall(query, limit),search_recall_semantic(),search_recall_summary(),load_full(id),backfill_recall_embeddings() - Embedding model:
sentence-transformers/all-MiniLM-L6-v2(384d, local, zero API cost). If missing, Mnemos falls back transparently to FTS5 — zero breaking changes. - Progressive disclosure:
search_recall_summary()returns snippet-only results (Layer 1),load_full(id)fetches the full entry on demand (Layer 2). Target: ~10× token reduction on recall. - Compaction: No auto-compaction. Sleep-time Aurora (P3) may prune after measuring access ROI.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 205 lines · 89 tokens per session scan A 39de636c68bb
mnemos is a skill published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 2,651 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 2026-08-31.
Other skills, from other repositories
cco-patterns
Share learned file patterns across a team — export an anonymized digest of what's usually waste/useful/co-edited, and import a teammate's so a fresh clone benefits day one.
dream
Prunes and consolidates the project's auto-memory to keep it minimal — deletes stale, wrong, or redundant memories, merges overlapping ones into existing files, and trims the index. Strong bias against growth: never creates new memory files and never stores new facts. Verifies staleness against the current codebase…
team-memory-protocol
A shared-memory process for teams of coding agents working on the same build. It stores project knowledge, shared context, and task progress in separate files or repositories.
magic-compact
Compact this Claude Code session.
knowledge-wiki
A tool that turns useful lessons from coding sessions into general articles for a team wiki. A wiki is a collection of linked reference pages, and this one can be kept locally or shared through a Git repository.
memem-mine
Opt in to memem's event-triggered mining. New sessions are mined automatically via the Stop hook.