tiered-memory SKILL.md skillA

This file is byte-identical to the first copy the registry indexed, one of 4 indexed copies. Same content hash, so the same checks give both the same grade.

tiered-memory from microsoft/waza is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add microsoft/waza/tiered-memory@git:20261016.42d1b9f

Pins git:20261016.42d1b9f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
microsoft/waza
Path
.github/skills/tiered-memory/SKILL.md
Versions recorded
1
Latest version
git:20261016.42d1b9f, committed Oct 16, 2026
Size
7,506 bytes
Repository stars
1,511
License
MIT

Three-tier agent memory model (hot/cold/wiki) for context reduction per spawn.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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](https://github.com/bradygaster/squad/issues/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.
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_qd2lm7afqgztt3t3/e35e50f23e635aede8ca0104c07be7673c2027ae5305cbcc96f749d3d7efaff6.json

Then /plugin install tiered-memory@markdownregistry-qd2lm7afqgztt3t3 in Claude Code. It installs git:20261016.42d1b9f, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add microsoft/waza/tiered-memory@sha256:e35e50f23e635aed

The line at the top of this page pins the label git:20261016.42d1b9f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_qd2lm7afqgztt3t3.svg)](https://markdownregistry.com/a/art_qd2lm7afqgztt3t3)

4 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in microsoft/waza/tiered-memory since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of tiered-memory from somewhere else? Ask it: where did my tiered-memory come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Oct 16, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261016.42d1b9f latest2026-10-16 42d1b9f 7,506 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7506 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

microsoft/waza · 1,511 stars · license MIT · pushed 2026-11-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_qd2lm7afqgztt3t3
GET https://markdownregistry.com/api/v1/resolve?ref=microsoft/waza/tiered-memory
GET https://markdownregistry.com/api/v1/blob/e35e50f23e635aede8ca0104c07be7673c2027ae5305cbcc96f749d3d7efaff6

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from microsoft/waza

squad-commands SKILL.md skill
microsoft/waza · .copilot/skills/squad-commands/SKILL.md · Categorized catalog of common Squad operations. Coordinator reads this file and presents it as an interactive menu when…
git:20260615.284ec6d · audit A · 1,511 stars
agent-collaboration SKILL.md skill
microsoft/waza · .github/skills/agent-collaboration/SKILL.md · Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
git:20261016.42d1b9f · audit A · 1,511 stars
azd-publish SKILL.md skill
microsoft/waza · .github/skills/azd-publish/SKILL.md · Prepare and publish a new version of the waza azd extension. USE FOR: "publish extension", "release new version", "bump…
v1.0 · audit A · 1,511 stars
coordinator-init-mode SKILL.md skill
microsoft/waza · .github/skills/coordinator-init-mode/SKILL.md · The complete two-phase Init Mode protocol the Squad coordinator runs when no team exists yet in the current repo. Phase…
git:20261028.6e8c54d · audit A · 1,511 stars
coordinator-response-mode SKILL.md skill
microsoft/waza · .github/skills/coordinator-response-mode/SKILL.md · Selecting WHO handles work is the Routing table; selecting HOW they handle it (Direct, Lightweight, Standard, Full) is…
git:20261016.42d1b9f · audit A · 1,511 stars
coordinator-source-of-truth SKILL.md skill
microsoft/waza · .github/skills/coordinator-source-of-truth/SKILL.md · The complete file-by-file source-of-truth hierarchy for Squad: which files are authoritative, which are…
git:20261016.42d1b9f · audit A · 1,511 stars
cross-squad-communication SKILL.md skill
microsoft/waza · .github/skills/cross-squad-communication/SKILL.md · Protocol for sending queries, delegating tasks, and sharing context between independent Squad instances across…
git:20261016.42d1b9f · audit A · 1,511 stars
cross-squad SKILL.md skill
microsoft/waza · .github/skills/cross-squad/SKILL.md · Coordinating work across multiple Squad instances — discovery, delegation, and disambiguation when the user says…
git:20261016.42d1b9f · audit A · 1,511 stars
error-recovery SKILL.md skill
microsoft/waza · .github/skills/error-recovery/SKILL.md · Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.
git:20261016.42d1b9f · audit A · 1,511 stars
git-workflow SKILL.md skill
microsoft/waza · .github/skills/git-workflow/SKILL.md · Squad branching model: dev-first workflow with insiders preview channel
git:20261016.42d1b9f · audit A · 1,511 stars
iterative-retrieval SKILL.md skill
microsoft/waza · .github/skills/iterative-retrieval/SKILL.md · Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to…
git:20261016.42d1b9f · audit A · 1,511 stars
reflect SKILL.md skill
microsoft/waza · .github/skills/reflect/SKILL.md · Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating…
v1.0.0-squad · audit A · 1,511 stars

Every file in microsoft/waza

Other files named tiered-memory

tiered-memory SKILL.md skill
bradygaster/squad · packages/squad-cli/templates/skills/tiered-memory/SKILL.md · Three-tier agent memory model (hot/cold/wiki) for context reduction per spawn
git:20260910.9cf5842 · audit A · 5 stars
tiered-memory SKILL.md skill
bradygaster/squad · .squad-templates/skills/tiered-memory/SKILL.md · Three-tier agent memory model (hot/cold/wiki) for context reduction per spawn
git:20260910.9cf5842 · audit A · 5 stars
tiered-memory SKILL.md skill
bradygaster/squad · packages/squad-sdk/templates/skills/tiered-memory/SKILL.md · Three-tier agent memory model (hot/cold/wiki) for context reduction per spawn
git:20260910.9cf5842 · audit A · 5 stars

Browse by kind, by grade A, or by owner.

Kept in .github/skills, the folder GitHub Copilot reads. More agent skills for GitHub Copilot.