tiered-memory

tiered-memory is a skill for Claude Code, Codex from github/gh-aw. It costs 20 tokens per session (1,758 once invoked), scanned A, original, MIT.

A proposed three-level memory model for agents: current-session notes, older context, and a reference knowledge base.

In plain words
What is it for?
It is for planning how agent context can be split, retained, promoted, and loaded only when relevant.
Why use it?
It aims to stop every new agent session from loading the entire growing history, though the underlying runtime support is not yet shipped.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one.

Good fit It is for planning how agent context can be split, retained, promoted…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/github/gh-aw/tiered-memory
About the project

GitHub Agentic Workflows is a GitHub CLI extension that lets developers define AI-assisted repository automation in Markdown and run it through GitHub Actions. It is intended for tasks requiring interpretation or reasoning, such as issue triage, pull-request review, CI investigation, documentation maintenance, and dependency analysis. The catalogue entries provide skills and agents for working with these workflows.

github/gh-aw · 5,108 stars · on GitHub · gh.io

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.

Any agent
npx skills add github/gh-aw --skill tiered-memory
Clone the repo
git clone --depth 1 https://github.com/github/gh-aw

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/github/gh-aw/tiered-memory.svg)](https://agentmods.dev/skills/github/gh-aw/tiered-memory)
Your own site
<a href="https://agentmods.dev/skills/github/gh-aw/tiered-memory"><img src="https://agentmods.dev/badge/skills/github/gh-aw/tiered-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,758 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00020 $0.01758
Opus 5 $0.00010 $0.00879
Sonnet 5 $0.00004 $0.00352
Haiku 4.5 $0.00002 $0.00176

Measured 3d ago against content hash f9aa7ffa3685, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.squad/templates/skills/tiered-memory/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Tiered Agent Memory

Status (v0.10.0): This skill describes a design proposal, not a shipped runtime. Skill files install via squad init/upgrade, but the underlying tier scaffolding (.squad/memory/hot/, cold/, wiki/), Scribe promotion logic, and spawn-template tier-aware reads are tracked in bradygaster/squad#1264. Until those land, agents continue to load full history.md + decisions.md on every spawn.

Overview

Squad agents today load their full context history on every spawn, which grows unboundedly across sessions. The Tiered Agent Memory model proposes a three-tier separation so agents only load the bytes that are actually relevant to the current task, with older context kept available on demand.


Memory Tiers

🔥 Hot Tier — Current Session Context

  • Size target: keep small (~2–4KB typical)
  • 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: larger summary, not full transcript (~8–12KB typical)
  • 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: Rolling window (default proposal: 30 days). Eligible entries are then promoted to Wiki.
  • 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.

Read the full file on GitHub · 222 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. 3d ago First seen · 222 lines · 20 tokens per session scan A f9aa7ffa3685

Subscribe to this mod's changes

tiered-memory is a skill published in the GitHub repository github/gh-aw (5,108 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 1,758 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 2026-09-03.

Related

Other skills, from other repositories

codspeed-optimize

Autonomously optimize code for performance using CodSpeed benchmarks, flamegraph analysis, and iterative improvement. Use this skill whenever the user wants to make code faster, reduce CPU usage, optimize memory, improve throughput, find performance bottlenecks, or asks to 'optimize', 'speed up', 'make faster'…

CodSpeedHQ/codspeed · 113 tokens

Context Management

Compress long interaction history into useful state for future agent turns.

Raidriar7170/hermes-skilleval · 15 tokens

c-github

Interact with GitHub using the gh CLI and jq. Manage PRs, issues, repositories, and Actions workflows. Make raw API calls with gh api for anything not covered by built-in commands.

daxaur/openpaw · 48 tokens

watch-pr

Watch a GitHub pull request for CI status, reviews, comments, merge conflicts, and terminal states using the gh-watch extension. Use when the user wants to monitor a PR, wait for CI, or track PR progress.

justincampbell/gh-watch · 48 tokens

watch-tag

Watch a GitHub repository for new tags using the gh-watch extension. Use when the user wants to be notified when a tag is created, when a release is cut, or when a tag that includes a specific commit appears (e.g. "tell me when my merge ships in a release").

justincampbell/gh-watch · 62 tokens

watch-branch

Watch a GitHub branch for new commits using the gh-watch extension. Use when the user wants to be notified when new commits are pushed to a branch, monitor main for merges, or track branch activity.

justincampbell/gh-watch · 45 tokens