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 matrixorigin/memoria --skill thememoriagit clone --depth 1 https://github.com/matrixorigin/memoriaWrote 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/matrixorigin/memoria/thememoria)<a href="https://agentmods.dev/skills/matrixorigin/memoria/thememoria"><img src="https://agentmods.dev/badge/skills/matrixorigin/memoria/thememoria/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/matrixorigin/memoria/thememoria"><img src="https://agentmods.dev/badge/skills/matrixorigin/memoria/thememoria.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 | $0.00070 | $0.00683 |
| Opus 5.5 | $0.00028 | $0.00273 |
| Sonnet 5.5 | $0.00014 | $0.00137 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
thememoria 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 2mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memoria
Use this skill when OpenClaw should treat Memoria as the durable external memory system for the current user or project.
Routing
Pick the smallest reference that matches the task:
- Install or verify the OpenClaw plugin:
references/setup.md - Decide which memory tool to use:
references/tool-surface.md - Daily store, recall, correct, forget behavior:
references/operations.md - Session lifecycle, goals, recovery, branches, rollback:
references/patterns.md
Core Rules
- Prefer Memoria tools over
MEMORY.mdormemory/YYYY-MM-DD.mdunless the user explicitly asks for file-based notes. - Do not auto-store every turn. Save durable facts, preferences, decisions, workflows, and meaningful progress.
- On task resume or "what do you remember" prompts, retrieve relevant memory first.
- Use the most specific tool available:
memory_profilefor stable preferences,memory_storefor general durable memory,memory_correctormemory_forgetfor repairs. - Before bulk delete, purge, or large rewrites, create a snapshot first.
- Use branches for risky or reversible memory experiments, then diff and merge or delete.
- After important writes, repairs, rollback, or merges, verify with retrieval or list tools.
- Do not claim only
memory_searchormemory_getexist when othermemory_*tools are available.
Default Flow
- At conversation start or task resume, use
memory_retrieveormemory_searchfor relevant context. - During the conversation, store only the durable facts worth keeping.
- If the user corrects or removes memory, repair it immediately with
memory_correct,memory_forget, ormemory_purge. - For risky memory maintenance, create a snapshot or branch before mutating state.
- At the end of meaningful work, store the durable outcome and clean up obsolete working memory.
Important Notes
- OpenClaw's built-in file memory (
openclaw memory) is separate from Memoria (openclaw memoria). - The plugin defaults to explicit writes, not silent auto-capture.
memory_getis a compatibility helper; when in doubt, prefermemory_retrieve,memory_search, ormemory_list.- Memoria's core strengths are semantic retrieval, durable cross-session memory, snapshots, rollback, branches, merge, and governance.
What ships with it
4 files 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.
- 2mo ago First seen · 61 lines · 70 tokens per session scan A 143483252e7c
thememoria is a skill published in the GitHub repository matrixorigin/memoria (623 stars, last pushed 2d ago), licensed Apache-2.0. It adds 70 tokens to every session and 683 once invoked, about $0.0003 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.
thememoria compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| thememoriamatrixorigin/memoria | Skill | 623 | 2d ago | Apache-2.0 | A | 70 | Claude Code, Codex |
| sensors-add-skilltoejough/engram | Skill | 10 | 13d ago | Apache-2.0 | A | 30 | Claude Code, Codex |
| review-prsgoogleapis/mcp-toolbox | Skill | 17k | yesterday | Apache-2.0 | A | 162 | Claude Code, Codex |
| reproduce-buggoogleapis/mcp-toolbox | Skill | 17k | yesterday | Apache-2.0 | A | 130 | Claude Code, Codex |
| fix-failing-testsgoogleapis/mcp-toolbox | Skill | 17k | yesterday | Apache-2.0 | A | 87 | Claude Code, Codex |
| stale-sweepgoogleapis/mcp-toolbox | Skill | 17k | yesterday | Apache-2.0 | A | 159 | Claude Code, Codex |
| triage-issuesgoogleapis/mcp-toolbox | Skill | 17k | yesterday | Apache-2.0 | A | 164 | Claude Code, Codex |