remember

A command for saving a preference, permission, or project-specific fact in the appropriate configuration or memory file.

In plain words
What is it for?
Use it to record behaviors such as always running tests, approved commands, or facts like a project's API path.
Why use it?
It removes the need to repeat instructions and helps keep personal rules separate from project details.

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/ds1/boilerplate.md/remember
Clone the repo
git clone --depth 1 https://github.com/ds1/boilerplate.md
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 453 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00000 $0.00453
Opus 5 $0.00000 $0.00227
Sonnet 5 $0.00000 $0.00091
Haiku 4.5 $0.00000 $0.00045

Measured 2d ago against content hash cc7a7d23e26a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

remember scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**Tool permission** (goes in `~/.claude/settings.json` under `permissions.allow`):
commands/remember.md · 48 lines

What it actually says

Remember Global Preference

Save a global preference or behavior based on the user's natural language description.

Usage

/remember <description of desired behavior>

Steps

  1. Parse the user's description and classify it:

    Tool permission (goes in ~/.claude/settings.json under permissions.allow):

    • "allow rm commands" -> add Bash(rm:*)
    • "allow docker" -> add Bash(docker:*)
    • "let me use bun" -> add Bash(bun:*)
    • Any request to auto-approve a specific command or tool

    Behavioral instruction (goes in ~/.claude/CLAUDE.md):

    • "always run tests after changes"
    • "prefer bun over npm"
    • "don't auto-commit"
    • "use tabs not spaces"
    • Any preference about how Claude should work, communicate, or make decisions

    Project memory (goes in the current project's memory/MEMORY.md):

    • "this project uses port 4000"
    • "the API is at /v2 not /v1"
    • Any fact specific to the current project, not global
  2. Show the user:

    • What will be saved
    • Where it will be saved (file path)
    • The exact content being added
  3. Save it to the appropriate file:

    • settings.json: Add to the permissions.allow array
    • CLAUDE.md: Append under the most relevant existing section, or create a new ## User Preferences section if none fits
    • memory/MEMORY.md: Append under a relevant heading or create one
  4. Confirm: "Saved to [file]. This will persist across all future sessions."

Classification Priority

If unclear, default to ~/.claude/CLAUDE.md. Behavioral instructions are the most common case.


By @ds1boilerplate.md

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 · 48 lines · 0 tokens per session scan B cc7a7d23e26a

Subscribe to this mod's changes

remember is a command published in the GitHub repository ds1/boilerplate.md (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 453 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.