Memory
Manage SSOT, memory, and cross-tool memory search. Guardian of decisions.md and patterns.md. Use when user mentions memory, SSOT, decisions.md, patterns.md, merging, migration, SSOT promotion, sync memory, save learnings, memory search, harness-mem, past decisions, or record this. Do NOT load for: implementation work, reviews, ad-hoc notes, or in-session logging.From its SKILL.md
npx -y skills add aiskillstore/marketplace --skill memoryAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
SKILL.md
3.5 KB, 742 tokens by cl100k_base, as published. Nobody here has run it
Memory Skills
メモリとSSOT管理を担当するスキル群です。
機能詳細
| 機能 | 詳細 |
|---|---|
| SSOT初期化 | See references/ssot-initialization.md |
| Plans.mdマージ | See references/plans-merging.md |
| 移行処理 | See references/workflow-migration.md |
| プロジェクト仕様同期 | See references/sync-project-specs.md |
| メモリ→SSOT昇格 | See references/sync-ssot-from-memory.md |
Unified Harness Memory（共通DB）
Claude Code / Codex / OpenCode 共通の記録・検索は harness_mem_* MCP を優先する。
- 検索:
harness_mem_search,harness_mem_timeline,harness_mem_get_observations - 注入:
harness_mem_resume_pack - 記録:
harness_mem_record_checkpoint,harness_mem_finalize_session,harness_mem_record_event
Claude Code 自動メモリとの関係（D22）
Harness の SSOT メモリ（Layer 2）は Claude Code の自動メモリ（Layer 1）と共存します。
自動メモリは汎用的な学習を暗黙的に記録し、SSOT はプロジェクト固有の意思決定を明示的に管理します。
Layer 1 の知見がプロジェクト全体に重要な場合、/memory ssot で Layer 2 に昇格してください。
実行手順
- ユーザーのリクエストを分類
- 上記の「機能詳細」から適切な参照ファイルを読む
- その内容に従って実行
SSOT昇格
メモリシステム（Claude-mem / Serena）から重要な学びをSSOTに永続化します。
- "Save what we learned" → references/sync-ssot-from-memory.md
- "Promote decisions to SSOT" → references/sync-ssot-from-memory.md
What ships with it: 6 files
58.8 KB alongside SKILL.md
references/
- plans-merging.md5.9 KB
- ssot-initialization.md1.2 KB
- sync-project-specs.md2.9 KB
- sync-ssot-from-memory.md3.8 KB
- workflow-migration.md4.6 KB
- skill-report.json40.4 KB
Gives 0 of the 12 instructions most memory context skills give in 742 tokens
Counted across 754 of the 1,056 authors here whose files we hold, read 2026-09-06
- Preserve existing content structurein 15 of 754, across 9 files
- Front-load the leading wordin 14 of 754, across 10 files
- Update existing entries instead of duplicatingin 14 of 754, across 7 files
- Keep CLAUDE.md under one hundred linesin 14 of 754, across 12 files
- Read CLAUDE.md at the project rootin 14 of 754
- Keep each meaning in a single source of truthin 12 of 754, across 8 files
- Redact sensitive information before committingin 11 of 754, across 4 files
- Scan for all CLAUDE.md filesin 11 of 754, across 7 files
- Use frontmatter for metadata on filesin 10 of 754, across 3 files
- Repeat user interactions 10 timesin 10 of 754, across 4 files
- Write the CLAUDE.md file into the target folderin 10 of 754, across 8 files
- Use memlab to process snapshotsin 9 of 754, across 3 files
Said here and by no other author read
- Prioritize harness_mem tools for memory search
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.