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.
git 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/commands/alibaizhanov/mengram/weekly)<a href="https://agentmods.dev/commands/alibaizhanov/mengram/weekly"><img src="https://agentmods.dev/badge/commands/alibaizhanov/mengram/weekly/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/commands/alibaizhanov/mengram/weekly"><img src="https://agentmods.dev/badge/commands/alibaizhanov/mengram/weekly.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00012 | $0.00135 |
| Opus 5 | $0.00006 | $0.00068 |
| Sonnet 5 | $0.00002 | $0.00027 |
| Haiku 4.5 | $0.00001 | $0.00014 |
Grade A, and why
weekly 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 9d 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
Run the shell command mengram weekly and show its full output to the user verbatim inside a code block (it is a pre-formatted box — do not reflow, summarize, or annotate it).
If the user asks to share it, run mengram weekly --share instead — it also prints a ready-to-post summary and copies it to the clipboard.
If the mengram command is not found, tell the user to run: pip install --upgrade mengram-ai (the weekly report needs mengram-ai >= 2.29.0).
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.
- 9d ago First seen · 10 lines · 12 tokens per session scan A 2d2aedfafc18
weekly is a command published in the GitHub repository alibaizhanov/mengram (192 stars, last pushed yesterday), licensed Apache-2.0. It adds 12 tokens to every session and 135 once invoked, about $0.0001 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 commands, from other repositories
iai-directive
Record a standing order the user typed themselves, as an explicit memory directive.
log
Command "log" from allenc84/sapience, covering /log — judgment ledger command, routing, new assessment: /log, review: /log review [domain] and resolve: /log resolve.
digest
A command for creating hierarchical digests from episodic retrieval-augmented generation, or EpisodicRAG. The description specifies digest levels covering eight layers and 100 years.
dream-defrag
A command for pruning Claude Code’s saved memory files, including MEMORY.md and other memory notes.
context-preload
A command for managing and setting up ContextPreloader.
recall
Answer from reef memory, reading the pages before answering.