memory-system

A file-based memory system for preserving user preferences, project conventions, and past decisions across coding-agent sessions.

In plain words
What is it for?
Use it when the agent should remember preferences, technical decisions, project rules, or feedback beyond the current session.
Why use it?
It prevents the agent from starting over or repeatedly asking for information that was already established.

Skill for Claude CodeCodex

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 skills/phuonghx/aim-cli/memory-system
Any agent
npx skills add phuonghx/aim-cli --skill memory-system
Clone the repo
git clone --depth 1 https://github.com/phuonghx/aim-cli

Made for: Claude Code, Codex.

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,439 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 $0.00086 $0.01439
Opus 5 $0.00043 $0.00720
Sonnet 5 $0.00017 $0.00288
Haiku 4.5 $0.00009 $0.00144

Measured yesterday against content hash 2e891c40c51d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-system 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.

aim/templates/aim-agents/skills/memory-system/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory System

Without memory, every session starts from zero — preferences re-explained, conventions re-discovered, decisions re-litigated. This skill fixes that by keeping a small, searchable record on disk. A short index points to detailed topic files, so the agent can pull back exactly what it needs.

The trade is favorable: loading the index costs roughly a thousand tokens, while skipping the re-discovery it replaces saves several thousand.

How It's Laid Out

.aim-agents/memory/
├── MEMORY.md                 ← the index — a thin set of pointers, ≤200 lines
├── user-preferences.md       ← who the user is: role, style, tooling
├── project-conventions.md    ← how this project does things
├── tech-decisions.md         ← architectural calls already made
├── feedback-history.md       ← what landed well or badly
└── <topic>.md                ← more topic files as the need arises

The Index File

MEMORY.md is a directory, not a database. Each line is a one-glance summary that names the topic file holding the full story.

Keep it disciplined:

  • Cap the whole file at 200 lines.
  • Hold each entry to about 150 characters.
  • Use the shape: - [type] summary → topic-file.md.
  • Stick to four tags: [user], [feedback], [project], [reference].

A worked example:

# Memory Index

## User
- [user] Works on macOS, lives in the terminal, prefers fish → user-preferences.md
- [user] Staff backend engineer, ~10 yrs in distributed systems → user-preferences.md
- [user] Writes in English; occasional German → user-preferences.md

## Project
- [project] pnpm only — never npm or yarn → project-conventions.md
- [project] React 19 with the compiler on → tech-decisions.md
- [project] Trunk-based; short-lived branches off main → project-conventions.md

## Feedback
- [feedback] Wants answers tight, no preamble → feedback-history.md
- [feedback] Finds long walkthroughs tedious → feedback-history.md
- [feedback] Reaches for tables over bullet lists → feedback-history.md

## Reference
- [reference] Staging gateway listens on 8443 → infrastructure-notes.md
- [reference] Release flow: tag, then CI promotes → project-conventions.md

Read the full file on GitHub · 159 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. yesterday First seen · 159 lines · 86 tokens per session scan A 2e891c40c51d

Subscribe to this mod's changes

memory-system is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 1,439 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

hs-release

Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.

vectorize-io/hindsight · 45 tokens

hindsight-local

Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).

vectorize-io/hindsight · 32 tokens

research-repository

Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.

Owl-Listener/designer-skills · 43 tokens

design-negotiation

Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).

Owl-Listener/designer-skills · 48 tokens

user-persona

Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use empathy-map; for motivation framing use jobs-to-be-done.

Owl-Listener/designer-skills · 50 tokens

version-control-strategy

Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).

Owl-Listener/designer-skills · 50 tokens