Borrowing it
Nothing to install: this file belongs to sabbour/agentweaver. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sabbour/agentweaver/dev/.github/skills/tiered-memory/SKILL.mdgit clone --depth 1 https://github.com/sabbour/agentweaverWrote 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.
[](https://agentmods.dev/skills/sabbour/agentweaver/tiered-memory)<a href="https://agentmods.dev/skills/sabbour/agentweaver/tiered-memory"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/tiered-memory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sabbour/agentweaver/tiered-memory"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/tiered-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00020 | $0.01758 |
| Opus 5.5 | $0.00008 | $0.00703 |
| Sonnet 5.5 | $0.00004 | $0.00352 |
| Haiku 4.5 | $0.00002 | $0.00176 |
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 1mo 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.
This is a copy
100% identical to tiered-memory — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 221 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 fullhistory.md+decisions.mdon 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-coldin spawn template or add## Cold Memorysection.
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.
- 1mo ago First seen · 221 lines · 20 tokens per session scan A 61ed1c582fc7
tiered-memory is a skill published in the GitHub repository sabbour/agentweaver (7 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 5.5. A static security scan graded it A with 0 findings. It is 100% identical to tiered-memory, differing in 1 line, and is treated as a copy.
Other skills, from other repositories
wiki-ingest
Use when an operation issue asks to ingest a captured raw/ source into the LLM Wiki, or the user says "ingest ". Create durable source, entity, concept, synthesis, index, and log pages; use paperclip-distill for Paperclip bundles.
claude-compaction-restore
Use when a Claude Code session is about to compact, has just compacted, reached its context limit, resumed after /compact, or must rebuild its working picture of a long-running seat from its own restore map, its JSONL transcript and the files it touched.
retiring-and-inheriting-a-seat
Use when you are a sitting agent near your context threshold (85%) and a PLANNED seat transition is due — retire deliberately and hand your seat to a fresh successor primed from a packet, rather than let compaction degrade you. Covers the handover packet, the append-only lineage ledger (one row per tenure)…
session-compaction-and-restore
Use when reasoning about what survives compaction/context-loss/restart/seat-refresh, designing a high-fidelity restore packet, or distinguishing native runtime resume vs fork vs artifact-backed mental-model rebuild. Covers the 4 failure modes that prevent honest restore (compacted seat drops hot potato; restore packet…
memory
Persist important outcomes from this step to long-term storage with automatic forgetting curve.
cross-channel-history-retrieval
A skill for searching the original messages from earlier chat sessions and channels when the current conversation does not contain enough history.