跳到正文
cccskills
免费在 GitHub 公开

tiered-memory

Plan how Squad agents separate current tasks, summarized history, and lasting reference knowledge so each launch receives relevant context. The skill provides loading rules and prompt templates; the supporting runtime is still a design proposal.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

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

查看安装方法

适用场景

  • Plan which context agents load at launch
  • Separate session history from lasting knowledge
  • Design context templates for interrupted work

包含的文件(1)

  • SKILL.md7.2 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

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.

📚 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.

When to Load Each Tier

SituationHotColdWiki
New task, no prior context needed✅❌❌
Resuming interrupted work✅✅❌
Debugging a recurring issue✅✅❌
Implementing against a spec/ADR✅❌✅
Onboarding to unfamiliar subsystem✅❌✅
Post-incident review✅✅✅

Spawn Template Pattern

The default spawn prompt should include Hot tier only:

## Memory Context

### Hot (current session)
{hot_context}

Add --include-cold when the task needs history:

## Memory Context

### Hot (current session)
{hot_context}

### Cold (summarized history — load on demand)
See: .squad/memory/cold/{agent-name}.md

Add --include-wiki when the task needs domain knowledge:

## Memory Context

### Hot (current session)
{hot_context}

### Wiki (durable reference)
See: .squad/memory/wiki/{topic}.md

Integration with Scribe Agent (design — not yet implemented)

Scribe is the proposed memory coordinator for this system. Once the runtime lands, Scribe will:

  1. End of session: Compress Hot → Cold summary (target: ~10% of session verbosity)
  2. Aged cold entries: Promote Cold → Wiki for decisions/facts that aged into stable knowledge
  3. On-demand wiki writes: Any agent can request Scribe to write a wiki entry mid-session

Until then, see the Scribe charter for current behavior: .squad/agents/scribe/charter.md


Implementation Checklist (tracked in #1264)

  • Scribe writes Hot context file at session start (.squad/memory/hot/{agent}.md)
  • Scribe compresses and writes Cold summary at session end
  • Spawn templates default to Hot-only
  • Coordinators add --include-cold / --include-wiki flags as needed
  • Wiki entries stored in .squad/memory/wiki/
  • Cold entries stored in .squad/memory/cold/ with rolling TTL

References


Spawn Template

Spawn Template: Agent with Tiered Memory

Use this template when spawning any Squad agent. By default it loads Hot tier only. Add optional sections as needed.


Task

{task_description}

WHY

{why_this_matters}

Success Criteria

  • {criterion_1}
  • {criterion_2}

Memory Context

🔥 Hot (always included)

Paste current session context here (~2–4KB target):

Current task: {task_description}
Active decisions: {decisions_this_session}
Last actions: {last_3_to_5_actions}
Blockers: {current_blockers_or_none}
Talking to: {current_interlocutor}

❄️ Cold (include when task needs history — add --include-cold)

Load on demand. Do not inline unless specifically needed.

Summarized cross-session history is at: .squad/memory/cold/{agent-name}.md

Include when:

  • Resuming interrupted work
  • Debugging a recurring issue
  • "What have we tried before?"

To load cold memory, add this section and fetch the file before spawning:

## Cold Memory Summary
{contents_of_.squad/memory/cold/{agent-name}.md}

📚 Wiki (include when task needs domain knowledge — add --include-wiki)

Load on demand. Reference specific wiki docs by path.

Wiki entries are at: .squad/memory/wiki/

Include when:

  • Implementing against an ADR or spec
  • Onboarding to unfamiliar subsystem
  • Need stable conventions or API contracts

To load wiki, add this section and reference the specific doc:

## Wiki Reference
{contents_of_.squad/memory/wiki/{topic}.md}

Escalation

If blocked or uncertain:

  • Architecture questions → @picard
  • Security concerns → @worf
  • Infrastructure/deployment → @belanna
  • Memory/history questions → @scribe

Notes

  • Hot tier is always included; keep it focused
  • Cold adds a summary; only include when history is relevant
  • Wiki adds variable size; only include specific relevant docs
  • Runtime backing is tracked in bradygaster/squad#1264 — until those changes land, this skill is design-only and agents continue to load full history.md + decisions.md on every spawn

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Coordinate work across AI agents with shared rules for locating team files, recording decisions and their reasons, and requesting help. It also defines who owns revisions after a reviewer rejects an artifact.

中文简介正在准备中。当前显示英语简介。

  • Locate team files across separate working directories
  • Record decisions that affect other agents
  • Request input from another specialist
github/gh-aw54222026年10月20日 更新

Set shared development rules for an agent team: keep specific agent names out of product code, tests, and CI configuration, verify affected tests before finishing, and record lessons learned from mistakes.

中文简介正在准备中。当前显示英语简介。

  • Share development rules across multiple agents
  • Keep team-specific agent names out of code and tests
  • Check affected tests before declaring work complete
github/gh-aw54222026年10月20日 更新

Routes requests to design, create, update, debug, or upgrade GitHub Agentic Workflows to the appropriate instructions. It helps the agent select a workflow-specific procedure and apply any additional rules defined for the repository.

中文简介正在准备中。当前显示英语简介。

  • Designing a new workflow through questions
  • Investigating failed runs and recurring errors
  • Upgrading workflows and addressing deprecations
github/gh-aw54222026年10月20日 更新

Prepare architecture proposals before implementation so the team can agree on a direction. Organize evidence, technical choices, effects on existing work, risks, and the first release’s scope into a document with clear recommendations and decision owners.

中文简介正在准备中。当前显示英语简介。

  • Proposing a major architecture change
  • Replanning milestones after a foundation change
  • Comparing technical options before seeking approval
github/gh-aw54222026年10月20日 更新

Update the gh-aw-firewall version used by gh-aw, rebuild generated files, and review release notes and configuration schemas, which define valid settings. It guides related code and test updates while identifying follow-up work that remains.

中文简介正在准备中。当前显示英语简介。

  • Updating the firewall version used by gh-aw
  • Reviewing release notes for integration changes
  • Checking configuration schema differences
github/gh-aw54222026年10月20日 更新

Review git and gh operations in gh-aw workflows to check credential availability for each repository. Identify missing token handoffs, risky expansions of limited checkouts, and error handling needed where credentials are intentionally unavailable.

中文简介正在准备中。当前显示英语简介。

  • Reviewing git operations after repository checkout
  • Checking tokens for private cross-repository access
  • Reviewing sparse and shallow checkout changes
github/gh-aw54222026年10月20日 更新

查看 github 的全部技能

报告此技能的问题