use-memory

use-memory is a skill for Claude Code, Codex from altertable-ai/skills. It costs 34 tokens per session (2,179 once invoked), scanned A, original, MIT.

A memory tool for keeping useful context and organisation knowledge between coding-agent sessions.

In plain words
What is it for?
Remembering definitions, thresholds, conventions, past discoveries, and working preferences.
Why use it?
It avoids starting every session from scratch and reduces repeated mistakes or explanations.

Skill for Claude CodeCodex

Part of the altertable plugin — 19 skills, 1 MCP server shipped together

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/altertable-ai/skills/use-memory
Any agent
npx skills add altertable-ai/skills --skill use-memory
Clone the repo
git clone --depth 1 https://github.com/altertable-ai/skills

Made for: Claude Code, Codex.

Or install altertable, the plugin that ships this one along with the rest of its 19 skills, 1 MCP server.

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 use-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/altertable-ai/skills/use-memory.svg)](https://agentmods.dev/skills/altertable-ai/skills/use-memory)
Your own site
<a href="https://agentmods.dev/skills/altertable-ai/skills/use-memory"><img src="https://agentmods.dev/badge/skills/altertable-ai/skills/use-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,179 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 $0.00034 $0.02179
Opus 5 $0.00017 $0.01090
Sonnet 5 $0.00007 $0.00436
Haiku 4.5 $0.00003 $0.00218

Measured 3d ago against content hash b55b001f67e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

use-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 3d 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.

skills/use-memory/SKILL.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use Memory

Purpose

Memory and knowledge transform agents from stateless tools into learning entities. Instead of starting fresh each run, agents can:

  • Recall what worked before
  • Avoid repeating mistakes
  • Apply organization-specific knowledge
  • Build expertise over time

Altertable distinguishes knowledge entries from memories:

  • Knowledge entries are durable reference material added by the team or synced from repositories. Use create_knowledge only when the user wants a stable source of truth recorded exactly.
  • Memories are learned observations from agent work, notifications, discoveries, and feedback. Use memory tools for patterns, preferences, and working context learned through analysis.

At the start of every workflow - proactively recall relevant context before taking action.

Search when:

  • Beginning a new analysis
  • Before creating discoveries or insights
  • When context from past runs would help
  • When working with familiar entities (tables, metrics, users)
  • When initialize returns relevant knowledge entries, read them before deciding

When to Create

Only after something valuable happens - quality over quantity.

Create a memory when:

  • A discovery was approved or rejected (learn from feedback)
  • You found an organization-specific pattern or threshold
  • A technique worked well (or failed in a specific context)
  • You learned something that would help future runs

Create a knowledge entry when:

  • The user gives a canonical metric definition, business rule, or operating procedure
  • The content should be durable, searchable, and applied exactly in future work
  • The source of truth is not already available through a connected repository or semantic model

Do not create memories for:

  • Routine success ("query returned results")
  • Minor details ("table has 1M rows")
  • Information easily re-discoverable
  • Duplicates of existing memories
  • Stable definitions that belong in the semantic layer or a knowledge entry instead

Read the full file on GitHub · 296 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 296 lines · 34 tokens per session scan A b55b001f67e9

Subscribe to this mod's changes

use-memory is a skill published in the GitHub repository altertable-ai/skills (7 stars, last pushed 9d ago), licensed MIT. It adds 34 tokens to every session and 2,179 once invoked, about $0.0002 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens