A command for saving one fact to the current day's memory note and, when it will remain useful, to longer-term project memory. It appends the fact without replacing existing notes.

Use it to capture a single lasting preference, project fact, reference, or short-lived note for the coding agent to recall later.

It prevents useful decisions, preferences, and project facts from being lost between sessions while keeping temporary notes in the daily record.

remember — Command by JansenAnalytics

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/jansenanalytics/claudex/remember

Clone the repo

git clone --depth 1 https://github.com/JansenAnalytics/claudex

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 584 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.

Model	Per session	Once invoked
Fable 5	$0.00016	$0.00584
Opus 5	$0.00008	$0.00292
Sonnet 5	$0.00003	$0.00117
Haiku 4.5	$0.00002	$0.00058

Measured yesterday against content hash e137e6fbc7f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

remember 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 yesterday.

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/remember.md · 42 lines

What it actually says

Frictionless memory capture. The fact to remember is: $ARGUMENTS

Capture exactly one fact, fast. No interrogation, no fluff.

Resolve date & time (Europe/Oslo): date=$(TZ=Europe/Oslo date +%Y-%m-%d) and time=$(TZ=Europe/Oslo date +%H:%M).
Append to today's daily note at ~/.claude-agent/memory/$date.md:
- If the file doesn't exist, create it with a # $date header.
- If there's no ## Quick notes section, add one.
- Append a bullet under it: - HH:MM — <the fact>.
- NEVER overwrite or rewrite existing content — append only. Read first, then Edit/Write.
Judge durability. Is this a LASTING user preference, feedback, project fact, or reference — something future-you should know weeks from now? Or just today's ephemera (a transient status, a one-off reminder)?
- Ephemeral → daily note is enough. Skip to step 4.
- Lasting → ALSO persist to cross-session auto-memory:
  - Dir: $HOME/.claude/projects/$(echo "$HOME/.claude-agent" | sed 's#[/.]#-#g')/memory/ (Claude Code derives the project dir by replacing / and . with -)
  - First check that dir's MEMORY.md and existing files for one covering the same fact. If found, UPDATE it (don't duplicate).
  - Otherwise write <slug>.md (short, hyphenated, type-prefixed e.g. user-/feedback-/project-/reference-) with frontmatter:
```
---
name: <slug>
description: "<one-line summary>"
metadata:
  node_type: memory
  type: user|feedback|project|reference
---
```
    followed by the fact + brief context (the why, dated).
  - Add a one-line pointer to MEMORY.md: - [Title](<slug>.md) — <one-line>.
Confirm to the user via Telegram (reply tool): exactly what was saved and where.
- Daily only: ✅ Noted in today's daily note: <fact>
- Durable too: ✅ Saved + persisted to durable memory (<type>): <fact> Keep it to one line. Don't restate the whole thing back twice.

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.

yesterday First seen · 42 lines · 16 tokens per session scan A e137e6fbc7f8

Subscribe to this mod's changes

remember is a command published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 584 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.

Memory and context Productivity

remember

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement