remember

A command that saves a concise summary of the current conversation to active persistent memory. It keeps only information likely to matter in a later session.

In plain words
What is it for?
Saving the main outcome, blockers, preferences, or follow-up actions from a coding session.
Why use it?
It prevents important project decisions and next steps from being forgotten without copying the whole conversation into memory.

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/codysnider/tagmem/remember
Clone the repo
git clone --depth 1 https://github.com/codysnider/tagmem
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 151 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 $0.00007 $0.00151
Opus 5 $0.00003 $0.00076
Sonnet 5 $0.00001 $0.00030
Haiku 4.5 $0.00001 $0.00015

Measured yesterday against content hash 5c5e7c0b3be3, 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.

assets/opencode/commands/remember.md · 17 lines

What it actually says

Save the current conversation into tagmem.

Requirements:

  • Write exactly one concise diary entry capturing the highest-signal outcome of this conversation so far.
  • Add only the minimum additional durable memory needed: decisions, blockers, preferences, or next steps that are likely to matter later.
  • Do not dump the whole conversation into memory.
  • Prefer the current project naming convention used for OpenCode sessions as the primary memory topic or tag context.
  • If $ARGUMENTS is present, use it as the topic override.
  • Keep the saved memory factual, compact, and useful for later retrieval.

If there is not enough substantive content yet, say so briefly instead of forcing low-value memory writes.

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. yesterday First seen · 17 lines · 7 tokens per session scan A 5c5e7c0b3be3

Subscribe to this mod's changes

remember is a command published in the GitHub repository codysnider/tagmem (15 stars, last pushed 3mo ago), licensed MIT. It adds 7 tokens to every session and 151 once invoked, about $0.0000 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.