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 skills/perseus-computing-llc/perseus/memory-cleanupnpx skills add Perseus-Computing-LLC/perseus --skill memory-cleanupgit clone --depth 1 https://github.com/Perseus-Computing-LLC/perseusWrote 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/perseus-computing-llc/perseus/memory-cleanup)<a href="https://agentmods.dev/skills/perseus-computing-llc/perseus/memory-cleanup"><img src="https://agentmods.dev/badge/skills/perseus-computing-llc/perseus/memory-cleanup.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 | $0.00069 | $0.02008 |
| Opus 5 | $0.00034 | $0.01004 |
| Sonnet 5 | $0.00014 | $0.00402 |
| Haiku 4.5 | $0.00007 | $0.00201 |
Grade A, and why
memory-cleanup 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 4d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Cleanup Skill
Audits and purges stale memory systems from a Perseus environment, keeping Perseus Vault as the single source of truth. Run after upgrading Perseus, after switching memory backends, or whenever memory feels noisy.
Philosophy
Retaining old context is not as important as staying on the latest tooling and pushing the envelope. Old memory systems accumulate noise, cause federation artifacts, and slow down recall. When in doubt, delete.
The live Perseus Vault index (~/.perseus/memory/) is always the source of
truth. Everything else is a candidate for removal.
Trigger Phrases
- "clean up memory"
- "purge stale memory systems"
- "memory cleanup"
- "reflect and clean"
- "audit memory"
Workflow
Step 1 — Audit All Memory Locations
Check for the following known memory system locations:
# Perseus (live — keep)
ls -lht ~/.perseus/memory/ # Perseus Vault BM25 index files
ls -lht ~/.perseus/checkpoints/ # Session waypoints
# Rovo Dev sessions (live — keep)
ls ~/.rovodev/sessions/
ls ~/.codex/memories/
# Stale systems (candidates for deletion)
ls ~/.mem0/ # Mem0 library (superseded by Perseus Vault)
ls ~/.mempalace/ # Mempalace (superseded by Perseus Vault)
ls ~/.cache/chroma/ # Orphaned Chroma vector stores
ls ~/.cache/code-nemo/ # Nemo memory (if present)
ls ~/.local/share/perseus/ # Old single-file perseus installs
Report findings in a table:
| Location | Last Modified | Size | Status |
|---|---|---|---|
~/.perseus/memory/ |
{date} | {N} files | ✅ Live — keep |
~/.perseus/checkpoints/ |
{date} | {N} files | ✅ Live — keep |
~/.mem0/ |
{date} | {size} | 🗑️ Stale — delete |
~/.mempalace/ |
{date} | {size} | 🗑️ Stale — delete |
~/.cache/chroma/ |
{date} | {size} | ⚠️ Check — may be active |
Step 2 — Check for Garbled Federation Artifacts
Perseus @memory with federation enabled can write low-quality blended
content from other workspaces. Check the newest memory files:
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.
- 4d ago First seen · 228 lines · 69 tokens per session scan A 843313b15ef8
memory-cleanup is a skill published in the GitHub repository Perseus-Computing-LLC/perseus (43 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 2,008 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
ai-chat
Guidance for improving the Windmill AI chat (copilot), especially global mode — tools, prompts, and context-window discipline. Use when editing chat tools, system prompts, or tool-result shapes under frontend/src/lib/components/copilot/chat, or when changing how the chat manages its context window.
memory-consolidation
Weekly synthesis of accumulated notes and memory optimization.
memory-triage
Persistent long-term memory protocol powered by mem0. Evaluate conversations for durable facts worth storing via memoryadd. Handles identity, preferences, decisions, configurations, rules, projects, and relationships. Loaded by the openclaw-mem0 plugin when skills mode is active.
mem0-dream
Consolidates stored memories by merging duplicates, resolving contradictions, and pruning stale entries. Use when memory count is high, search results feel noisy or repetitive, or periodic cleanup is needed to maintain memory quality.
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…