agentmods.dev

update-memory

update-memory is an agent for coding agents from shuchitajain/awesome-ai-setup. It costs 25 tokens per session (1,863 once invoked), scanned A, original, MIT.

An agent instruction for creating or updating MEMORY.md, a repository file that records important past decisions and patterns for future coding sessions.

In plain words
What is it for?
Use it to inspect the project and maintain a focused decision log for later AI sessions.
Why use it?
It helps coding agents avoid repeating rejected approaches or breaking architectural decisions.

Agent

not rated 5 3mo ago A scan 25 tokens original MIT
View the source file shuchitajain/awesome-ai-setup
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 agents/shuchitajain/awesome-ai-setup/update-memory
Clone the repo
git clone --depth 1 https://github.com/shuchitajain/awesome-ai-setup

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 update-memory

README.md
[![agentmods](https://agentmods.dev/badge/agents/shuchitajain/awesome-ai-setup/update-memory.svg)](https://agentmods.dev/agents/shuchitajain/awesome-ai-setup/update-memory)
Your own site
<a href="https://agentmods.dev/agents/shuchitajain/awesome-ai-setup/update-memory"><img src="https://agentmods.dev/badge/agents/shuchitajain/awesome-ai-setup/update-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,863 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 $0.00025 $0.01863
Opus 5 $0.00013 $0.00932
Sonnet 5 $0.00005 $0.00373
Haiku 4.5 $0.00003 $0.00186

Measured 4d ago against content hash 6743ec9f1c51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-memory 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 4d 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.

agents/update-memory.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update MEMORY.md

You are generating or updating a MEMORY.md file for this repository.

This file records decisions that should persist across AI sessions - architectural choices that were made (and should not be re-litigated), patterns that were abandoned (and should not be reintroduced), and anti-patterns specific to this codebase (that AI tools repeatedly get wrong).

MEMORY.md is a decision log, not documentation. It should be opinionated, direct, and focused on what AI tools need to know to avoid repeating past mistakes.

Step 1 - Read the Repository

Gather information to understand the current state and history.

Read these sources:

  1. Dependency manifest (pubspec.yaml, package.json, etc.) - what's currently used tells you what was chosen. Look for what's notably absent (e.g., no flutter_bloc in a Flutter project means BLoC was either never used or was removed).

  2. Primary source directory structure - the organizational pattern reveals architectural decisions.

  3. State management files - how state is currently structured and what pattern is used.

  4. Existing MEMORY.md or ARCHITECTURE.md if present - don't duplicate what's already there.

  5. Comments and TODOs in code - // TODO: migrate this, // legacy: remove after X, // do not use Provider here - these are explicit memory signals left by developers.

  6. Any CHANGELOG.md, DECISIONS.md, or ADR/ directory - formal decision records.

  7. Test files - the mock strategy reveals decisions about test boundaries.

If git is available:

  • Run git log --oneline -50 to see recent commit history. Migration commits, refactor commits, and "remove X" commits are strong signals.
  • Check for commits with messages like "migrate from X to Y", "remove deprecated", "switch to", "replace".

Reference Example (Optional)

Check for a reference example in this order:

  1. .ai/reference/*/MEMORY.md - if the user copied one during setup
  2. node_modules/awesome-ai-setup/examples/*/MEMORY.md - if the package is installed locally

Read the full file on GitHub · 210 lines

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. 4d ago First seen · 210 lines · 25 tokens per session scan A 6743ec9f1c51

Subscribe to this mod's changes

update-memory is an agent published in the GitHub repository shuchitajain/awesome-ai-setup (5 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 1,863 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 contextaiai-agentscontext-engineeringgithub-copilotmcp
Related

Other agents, from other repositories

memory-agent

Code with persistent memory - remembers preferences, decisions, and context across sessions.

timothywarner-org/copilot-memory-store · 15 tokens

python-architect

Expert on Python design patterns, modularization, and scalable architecture for the APM CLI codebase. Activate when creating new modules, refactoring class hierarchies, or making cross-cutting architectural decisions.

microsoft/apm · 45 tokens

algorithmic-patterns

Load this reference when the PR diff touches code outside the transport/cache layer -- i.e. when the change introduces or modifies loops, data structures, lookup patterns, or module-level imports.

microsoft/apm · 0 tokens

apm-expert

Expert on APM (Agent Package Manager). Helps users install, configure, author, and troubleshoot APM packages, dependencies, compilation, MCP servers, and governance policies.

microsoft/apm · 39 tokens

test-coverage-expert

Test-coverage expert paired with the DevX UX lens. Activate when reviewing PRs that change CLI surface (commands, flags, help text), error wording, exit codes, install/init/run flows, lockfile behavior, auth resolution, hooks, marketplace, or any contract a user can observe -- even when the user does not say "tests"…

microsoft/apm · 151 tokens

apm-primitives-architect

Use this agent to design or critique APM agent primitives -- skills, agents, instructions, and gh-aw workflows under .apm/ and .github/. Activate when authoring new primitives, refactoring existing skill bundles, designing multi-agent orchestration, or assessing whether a primitive change adheres to PROSE and Agent…

microsoft/apm · 74 tokens