tiered-memory

tiered-memory is a skill for Claude Code, Codex from Azure-Samples/eShopLite. It costs 25 tokens per session (1,804 once invoked), scanned A, original, MIT.

A three-level memory system for coding agents: recent session details, summarized past work, and longer-term reference information.

In plain words
What is it for?
Use it to organize agent context across sessions and load older decisions only when a task needs them.
Why use it?
It reduces the amount of old or irrelevant conversation loaded each time an agent starts.

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/azure-samples/eshoplite/tiered-memory
Any agent
npx skills add Azure-Samples/eShopLite --skill tiered-memory
Clone the repo
git clone --depth 1 https://github.com/Azure-Samples/eShopLite

Made for: Claude Code, Codex.

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 tiered-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/azure-samples/eshoplite/tiered-memory.svg)](https://agentmods.dev/skills/azure-samples/eshoplite/tiered-memory)
Your own site
<a href="https://agentmods.dev/skills/azure-samples/eshoplite/tiered-memory"><img src="https://agentmods.dev/badge/skills/azure-samples/eshoplite/tiered-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,804 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 $0.01804
Opus 5 $0.00013 $0.00902
Sonnet 5 $0.00005 $0.00361
Haiku 4.5 $0.00003 $0.00180

Measured 5d ago against content hash 9ee36cd7dac5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tiered-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 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

Copies of this mod

1 near-identical copy found in the catalogue:

.squad/templates/skills/tiered-memory/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Tiered Agent Memory

Overview

Squad agents currently load their full context history on every spawn, resulting in 34–74KB payloads per agent (8,800–18,500 tokens). Measurement shows 82–96% of that context is "old noise" — information that is no longer relevant to the current task. The Tiered Agent Memory skill introduces a three-tier memory model that eliminates this bloat, achieving 20–55% context reduction per spawn in production.


Memory Tiers

🔥 Hot Tier — Current Session Context

  • Size target: ~2–4KB
  • Load policy: Always loaded. Every spawn includes hot memory by default.
  • Contents: Current task description, active decisions made this session, immediate blockers, last 3–5 actions taken, who you are talking to right now.
  • Lifetime: Current session only. Discarded after session ends (Scribe promotes relevant parts to Cold).
  • Purpose: Provide immediate task context without any latency or load decision.

❄️ Cold Tier — Summarized Cross-Session History

  • Size target: ~8–12KB
  • Load policy: Load on demand. Include only when the task explicitly needs history.
  • Contents: Summarized past sessions (compressed by Scribe), cross-session decisions, recurring patterns, unresolved issues from prior work.
  • Lifetime: 30 days rolling window. After 30 days, Scribe promotes to Wiki tier.
  • Purpose: Answer "what have we tried before?" and "what was decided?" without replaying full transcripts.
  • How to include: Pass --include-cold in spawn template or add ## Cold Memory section.

📚 Wiki Tier — Durable Structured Knowledge

  • Size target: variable, structured reference docs
  • Load policy: Async write, selective read. Load only when task requires domain knowledge.
  • Contents: Architecture decisions (ADRs), agent charters, routing rules, stable conventions, external API contracts, known platform constraints.
  • Lifetime: Permanent until explicitly deprecated.
  • Purpose: Authoritative reference. Not history — structured facts.
  • How to include: Pass --include-wiki or reference specific wiki doc paths in spawn template.

Read the full file on GitHub · 235 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. 5d ago First seen · 235 lines · 25 tokens per session scan A 9ee36cd7dac5

Subscribe to this mod's changes

tiered-memory is a skill published in the GitHub repository Azure-Samples/eShopLite (168 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 1,804 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 2026-08-30.