mneme-record

mneme-record is a command for coding agents from MnemeHQ/mneme. It costs 8 tokens per session (265 once invoked), scanned A, a copy of record, MIT.

A command for saving a new architectural decision in the project's memory file. An architectural decision records a chosen approach, its reason, where it applies, and approaches to avoid.

In plain words
What is it for?
Use it to record project decisions, scopes, constraints, and anti-patterns, then confirm that the decision was added.
Why use it?
It keeps important design choices available to coding agents and future contributors instead of leaving them only in conversation or personal notes.

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/mnemehq/mneme/mneme-record
Clone the repo
git clone --depth 1 https://github.com/MnemeHQ/mneme

Wrote 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.

agentmods badge for mneme-record

README.md
[![agentmods](https://agentmods.dev/badge/commands/mnemehq/mneme/mneme-record.svg)](https://agentmods.dev/commands/mnemehq/mneme/mneme-record)
Your own site
<a href="https://agentmods.dev/commands/mnemehq/mneme/mneme-record"><img src="https://agentmods.dev/badge/commands/mnemehq/mneme/mneme-record.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 265 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00008 $0.00265
Opus 5 $0.00004 $0.00133
Sonnet 5 $0.00002 $0.00053
Haiku 4.5 $0.00001 $0.00026

Measured 5d ago against content hash 69aee8655b15, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mneme-record 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 5d 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.

Origin

This is a copy

100% identical to record — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

integrations/claude-code/commands/mneme-record.md · 34 lines

What it actually says

Ask the user for:

  • id — snake_case identifier (e.g. auth_001)
  • decision — one sentence stating the decision
  • rationale — why this decision was made
  • scope — list of keywords describing where this applies (used for retrieval — choose words that will appear in file names or task descriptions)
  • constraints — list of prohibited approaches
  • anti_patterns — list of specific strings/tokens to flag as violations

Then run via the Bash tool:

mneme add_decision \
  --memory .mneme/project_memory.json \
  --id <id> \
  --decision "<...>" \
  --rationale "<...>" \
  [--scope <keyword> ...] \
  [--constraint "<...>" ...] \
  [--anti-pattern "<...>" ...]

Confirm with:

mneme list_decisions --memory .mneme/project_memory.json

Scope tip: Choose scope keywords that will appear in file paths or task descriptions where this decision applies. The hook query is derived from the target file name — scope tokens that overlap with file names ensure the decision is retrieved during enforcement.

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. 5d ago First seen · 34 lines · 8 tokens per session scan A 69aee8655b15

Subscribe to this mod's changes

mneme-record is a command published in the GitHub repository MnemeHQ/mneme (20 stars, last pushed yesterday), licensed MIT. It adds 8 tokens to every session and 265 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to record, differing in 0 lines, and is treated as a copy.