hatirla

A quick command for saving one fact to memorry, a local searchable memory service that keeps information across sessions. It turns the supplied text into a self-contained note and stores it under a project.

In plain words
What is it for?
Use it when you want to remember a fact, preference, or project decision for later retrieval.
Why use it?
It makes persistent memory quicker to use while checking for older information that may need correction.

Command

Install

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.

agentmods
npx agentmods add commands/macbyclp/memorry/hatirla
Clone the repo
git clone --depth 1 https://github.com/macbyclp/memorry
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 457 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00457
Opus 5 $0.00005 $0.00229
Sonnet 5 $0.00002 $0.00091
Haiku 4.5 $0.00001 $0.00046

Measured 2d ago against content hash c51598d60642, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hatirla 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 2d 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.

commands/hatirla.md · 38 lines

What it actually says

The user wants this committed to persistent memory (memorry): $ARGUMENTS

Steps:

  1. Make sure the memorry server is running (port 8765). If it isn't, start it — on Windows via start-memory.bat, otherwise python server.py from your memorry checkout.
  2. Distill the text into ONE self-contained sentence — one that still makes sense read on its own months from now, with no surrounding conversation. If the user already phrased it that way, keep their wording; don't pad it with commentary.
  3. Search the same topic with memory_search first. If you find a record that is now stale or contradicts the new fact, remove it with memory_delete (or correct it in place with memory_update) before writing.
  4. Pick the right project. Keep personal facts and preferences separate from infrastructure/setup decisions — see the note below on setting your own default.
  5. Write a title of 3–6 words naming the topic (not a shortened copy of the sentence). It becomes the note's filename and its label in Obsidian's Graph View, so a truncated sentence there makes the graph unreadable.
  6. Add 1–3 tags, reusing tags already in use — check with memory_list if you don't know them. Tags are what group records into clusters and what the Graph View colours by; a new tag per record gives you neither.
  7. Save it with memory_add.
  8. Reply with a single line: what you saved and the id it got. No essay.

Customize this: step 4's routing is deliberately generic. Edit this file to name your own projects (e.g. personal vs infra, or one per codebase) and to hardcode the path to your start-memory.bat if you want step 1 to be a single copy-pasteable command.

Changes

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.

  1. 2d ago First seen · 38 lines · 11 tokens per session scan A c51598d60642

Subscribe to this mod's changes

hatirla is a command published in the GitHub repository macbyclp/memorry (3 stars, last pushed 15d ago), licensed MIT. It adds 11 tokens to every session and 457 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 2026-08-31.