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 Yeachan-Heo/clawhip --skill memory-offloadgit clone --depth 1 https://github.com/Yeachan-Heo/clawhipWrote 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/yeachan-heo/clawhip/memory-offload)<a href="https://agentmods.dev/skills/yeachan-heo/clawhip/memory-offload"><img src="https://agentmods.dev/badge/skills/yeachan-heo/clawhip/memory-offload.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00427 |
| Opus 5 | $0.00000 | $0.00214 |
| Sonnet 5 | $0.00000 | $0.00085 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
memory-offload 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 8d 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
clawhip × filesystem-offloaded memory
Use this skill when you want a Claw OS-style memory system where MEMORY.md stays small and points into a structured memory/ tree.
What you get
- a clear role for
MEMORY.mdas pointer/index/current-beliefs layer - a practical read/write workflow for agents
- guidance for sharding memory by time, channel, project, topic, and handoff
- migration guidance away from monolithic memory files
Read order
- Read
MEMORY.mdfirst. - Follow the pointer to the smallest relevant shard.
- Read subtree indexes only when needed.
- Avoid loading the whole memory tree by default.
Write order
- Write detailed updates to the canonical leaf shard.
- Update
MEMORY.mdonly when the pointer map or current beliefs changed. - If a section grows noisy, split it into a dedicated file.
- Archive cold history to keep the hot path small.
Default shard map
memory/daily/YYYY-MM-DD.md-> chronological execution logmemory/channels/<channel>.md-> one lane/channelmemory/projects/<project>.md-> project/repo statememory/agents/<agent>.md-> agent/operator profilememory/topics/rules.md-> durable operating rulesmemory/topics/lessons.md-> reusable lessonsmemory/handoffs/YYYY-MM-DD-<slug>.md-> bounded handoffsmemory/archive/YYYY-MM/-> cold history
Offload triggers
Offload when:
MEMORY.mdstops being easy to scan- one topic dominates the root file
- detail is only relevant to one entity or workflow
- logs or history start crowding out current beliefs
Start here
docs/memory-offload-architecture.mddocs/memory-offload-guide.mddocs/examples/MEMORY.example.mddocs/examples/memory/README.example.md
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.
- 8d ago First seen · 52 lines · 0 tokens per session scan A 5f8e8ca52319
memory-offload is a skill published in the GitHub repository Yeachan-Heo/clawhip (932 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 427 tokens. 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.