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 alibaizhanov/mengram --skill openclawgit clone --depth 1 https://github.com/alibaizhanov/mengramWrote 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/alibaizhanov/mengram/openclaw)<a href="https://agentmods.dev/skills/alibaizhanov/mengram/openclaw"><img src="https://agentmods.dev/badge/skills/alibaizhanov/mengram/openclaw/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/alibaizhanov/mengram/openclaw"><img src="https://agentmods.dev/badge/skills/alibaizhanov/mengram/openclaw.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 | $0.00053 | $0.01224 |
| Opus 5 | $0.00026 | $0.00612 |
| Sonnet 5 | $0.00011 | $0.00245 |
| Haiku 4.5 | $0.00005 | $0.00122 |
Grade A, and why
mengram-memory scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
metadata: {"openclaw":{"emoji":"🧠","requires":{"env":["MENGRAM_API_KEY"],"bins":["curl","python3"]},"primaryEnv":"MENGRAM_API_KEY","files":["scripts/*"]}} How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mengram Memory
Human-like long-term memory for your OpenClaw agent. Remembers facts, events, and workflows across all sessions and channels.
What This Skill Does
Mengram gives you 3 types of memory that work together:
- Semantic Memory — facts about the user (preferences, relationships, work, habits)
- Episodic Memory — events with timestamps and outcomes (meetings, trips, decisions)
- Procedural Memory — learned workflows with success/failure tracking (how-to steps)
All memory persists across sessions and channels. What you learn on WhatsApp is available on Discord.
Tools
This skill uses Bash to run scripts in {baseDir}/scripts/.
When To Use
ALWAYS search memory before answering questions about the user, their preferences, their history, or anything personal. This is critical — check memory first, then respond.
Save to memory after:
- The user shares personal information (name, preferences, habits, relationships)
- A task or event is completed (booking, deployment, purchase)
- A multi-step workflow is finished successfully or fails
- The user corrects you or provides new context
Get profile when:
- Starting a new session or conversation
- The user asks "what do you know about me"
- You need comprehensive context about the user
Scripts
1. Search Memory
Search all 3 memory types for relevant context. Do this before answering personal questions.
bash {baseDir}/scripts/mengram-search.sh "search query here"
Returns facts, past events, and known workflows matching the query. Use specific queries — "coffee preferences" not "stuff about user".
2. Save to Memory
Save conversation messages so Mengram can extract facts, events, and procedures automatically.
bash {baseDir}/scripts/mengram-add.sh "user said: I'm allergic to peanuts and my meeting with Sarah went well yesterday"
You can pass multiple messages. Mengram's AI automatically extracts:
- Facts → semantic memory ("user is allergic to peanuts")
- Events → episodic memory ("meeting with Sarah, yesterday, went well")
- Procedures → procedural memory (if workflow steps are described)
What ships with it
6 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.
- 11d ago First seen · 140 lines · 53 tokens per session scan A 53e252d78f7d
mengram-memory is a skill published in the GitHub repository alibaizhanov/mengram (194 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 1,224 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
digest-auto
A skill for analysing the current state of an EpisodicRAG system, which retrieves information from records of past events or work sessions.
memory-audit
An entry point for reviewing and maintaining an AI agent's stored memories. It describes how to remove repetition, preserve useful reasoning, and update memories when old conclusions no longer fit.
memory-audit-discoverability
A review guide for checking whether stored memories can be found at the right time. It focuses on where memories are attached, when they are triggered, whether aliases are missing, and whether a parent has too many children.
memory-audit-belief-duel
A guided review process for conflicting beliefs or memories. It examines cases where two conclusions cannot both be true, including conflicts between a general rule and a more specific memory.
memory-audit-node-decomposition
A method for splitting an oversized knowledge note into smaller notes, each focused on one independent idea. It also explains how to keep useful core information in the original note.
memory-audit-pattern-extraction
A method for investigating repeated mistakes by comparing related memories and checking whether an earlier reminder failed. It looks at where the reminder was stored, when it was created, and whether it was strong enough to prevent the mistake.