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 RikyZ90/ShibaClaw --skill memorygit clone --depth 1 https://github.com/RikyZ90/ShibaClawWrote 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/rikyz90/shibaclaw/memory)<a href="https://agentmods.dev/skills/rikyz90/shibaclaw/memory"><img src="https://agentmods.dev/badge/skills/rikyz90/shibaclaw/memory/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/skills/rikyz90/shibaclaw/memory"><img src="https://agentmods.dev/badge/skills/rikyz90/shibaclaw/memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00022 | $0.00468 |
| Opus 5.5 | $0.00009 | $0.00187 |
| Sonnet 5.5 | $0.00004 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
memory 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.
What it actually says
Memory
Structure
USER.md— Durable personal profile and preferences. Not token-compacted; keep it focused on long-lived user facts.memory/MEMORY.md— Operational long-term facts. Injected into every system prompt under# Memory, truncated from the bottom if it exceeds the token budget (~2000 tokens default).memory/HISTORY.md— Append-only log with[YYYY-MM-DD HH:MM] [#tag1 #tag2]entries. Never injected. Search it withmemory_searchor grep when historical context is missing.
MEMORY.md Layout
Sections are ordered by survival priority — top sections persist under truncation, bottom sections are dropped first.
## Environment— OS, runtime, tooling constraints, local services, provider setup## Entities— people, projects, repos, services referenced often## Project State— milestones, blockers, medium-term status, important decisions## Dynamic Context— current tasks, recent decisions, in-progress work
Rules:
- One fact per bullet, no prose paragraphs
- Update/replace existing facts instead of appending duplicates
- Put personal profile and preferences in
USER.md, not inmemory/MEMORY.md - Put durable operational facts in the top three MEMORY sections; only transient state goes in Dynamic Context
- Keep the file concise — the system auto-compacts when it exceeds ~1600 tokens
Missing Context
If a topic feels incomplete, search HISTORY.md first before assuming a fact was never recorded. Use the memory_search tool for semantic queries, or grep for exact matches:
grep -i "keyword" memory/HISTORY.md
Proactive Context Retrieval
If the user refers to past discussions or ongoing workflows you don't recall: search HISTORY.md before responding.
Auto-consolidation
Handled automatically every ~10 messages. Long-term memory is auto-compacted by the system when it grows beyond the configured threshold.
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 · 45 lines · 22 tokens per session scan A 18a8560190cf
memory is a skill published in the GitHub repository RikyZ90/ShibaClaw (84 stars, last pushed yesterday), licensed Apache-2.0. It adds 22 tokens to every session and 468 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
dify
Use when self-hosting an LLM app platform with visual orchestration — docker compose up in dify/docker, knowledge bases with hybrid retrieval + rerank, Chatflow/Workflow nodes (Knowledge Retrieval, Code, HTTP Request, Iteration), custom tools from OpenAPI schema, /v1/chat-messages and /v1/workflows/run API keys; also…
knowledge-audit
Review and clean up stored memories — find duplicates, contradictions, stale entries, and consolidate.
temporal-query
Answer time-travel questions over stored memory — what was believed at a past point in time, when a belief changed, and what replaced it. Use when the user says "as of", "back in", "at the time", "history of", "timeline", "what did I think then", or asks why a current memory contradicts an older one.
memory-commit
Use when the user explicitly says "remember this", "save this", "ghi nho", "luu lai", "save for next time", or otherwise asks to persist the immediately preceding context. Captures with the appropriate contexttype (decision, preference, fact, skill, task, conversation) so future sessions can retrieve it accurately.
recall-context
Use at session start, before significant decisions, or when a new task references a known project to recall mnemo memories matching the current working directory, recently edited files, or topic keywords. Helps maintain continuity across sessions and avoid redoing past research.
passport-bootstrap
Use when the user installs mnemo-mcp on a fresh machine and wants to restore prior memory state from S3 or Google Drive (Phase 2 passport sync). Triggers on phrases like "set up mnemo on this machine", "restore my memory passport", "import passport", "bootstrap mnemo", or when the user says they got a new laptop / VM…