[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AVRCMZJ6Q6FF6F8GTHZBTM":3,"skill-same:01M7AVRCMZJ6Q6FF6F8GTHZBTM":52},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7AVRCMZJ6Q6FF6F8GTHZBTM","ebbinghaus-memory-governor",null,"Govern conversational agent working memory retention using Ebbinghaus forgetting curves, channel decay multipliers, and non-linear recall stability reinforcement. Do not use for permanent database storage or ungrounded cache purges.","SpectreDeath\u002FBrain-Harness","SpectreDeath","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F207463416?v=4","01M7AVGR1D4X8ADT47APKGVH2Z","JL","01M7AVGR2HSGD23BA5DBTJJTVN",0,"MIT","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Febbinghaus-memory-governor\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ebbinghaus-memory-governor\ndescription: Govern conversational agent working memory retention using Ebbinghaus forgetting curves, channel decay multipliers, and non-linear recall stability reinforcement. Do not use for permanent database storage or ungrounded cache purges.\ncluster: memory_and_epistemics\n---\n\n# Ebbinghaus Memory Governor\n\n## Overview\n\nThe Ebbinghaus Memory Governor provides mathematical forgetting curve retention management for agent working memory. By modeling non-linear stability growth upon repeated recall, foundational instructions remain protected indefinitely while ephemeral tool outputs decay and soft-evict predictably.\n\n```\n┌─────────────────────────────────────────────────────────────┐\n│                 Turn Advance: step_turn()                   │\n└──────────────────────────────┬──────────────────────────────┘\n                               │\n       ┌───────────────────────┴───────────────────────┐\n       ▼                                               ▼\n┌──────────────────────────────┐        ┌──────────────────────────────┐\n│ is_foundational = True       │        │ is_foundational = False      │\n│ (Immune to Eviction)         │        │ R(t) = exp(-Δt \u002F (S \u002F m))    │\n└──────────────────────────────┘        └──────────────┬───────────────┘\n                                                       │\n                                        ┌──────────────┴───────────────┐\n                                        ▼                              ▼\n                         ┌─────────────────────────────┐ ┌─────────────────────────────┐\n                         │ R(t) >= 0.20                │ │ R(t) \u003C 0.20                 │\n                         │ ACTIVE IN WORKING SET       │ │ SOFT EVICTION               │\n                         │ Included in recall & prompt │ │ item.evicted = True         │\n                         │ S_new = S * (1 + ln(1 + n)) │ │ Preserved in item history   │\n                         └─────────────────────────────┘ └─────────────────────────────┘\n```\n\n---\n\n## Verified Soft-Demotion Semantics\n\nForgetting in this engine is **soft eviction (demotion from active working set), NOT permanent deletion**:\n1. **Turn-Based Retention Calculus**:\n   At each dialogue step $\\Delta t$, retention is computed as:\n   $$R(t) = \\exp\\left(-\\frac{\\Delta t}{S \u002F m_{\\text{channel}}}\\right)$$\n2. **Channel Decay Multipliers**:\n   Channel multipliers $m_{\\text{channel}}$ scale the rate of decay across 5 semantic channels (aligned with [Context Type System](..\u002Fcontext-type-system\u002FSKILL.md)):\n   - `instruction`: $0.25\\times$ (ultra-slow decay)\n   - `foundational`: $0.35\\times$ (slow decay)\n   - `evidence`: $0.70\\times$ (moderate decay)\n   - `memory`: $1.00\\times$ (standard baseline)\n   - `tool_output`: $1.75\\times$ (rapid decay)\n3. **Soft Eviction (`item.evicted = True`)**:\n   When $R(t) \u003C 0.20$, the item is marked as `evicted = True`. It is excluded from active `working_set()` and `recall()`, but **remains in memory storage** (`engine.items`) and is fully preserved in exported snapshot files and recoverable via `memory_query_working_set(include_evicted=True)`.\n4. **Foundational Immunity**:\n   Items with `is_foundational=True` bypass the retention check and are **never evicted**.\n5. **Non-Linear Stability Reinforcement**:\n   Recalling an active item increases its stability monotonically:\n   $$S_{\\text{new}} = S_{\\text{old}} \\cdot (1 + \\ln(1 + n_{\\text{recalls}}))$$\n\n---\n\n## Visual Brief\n\n### Architecture\n- **Logical Turn Clock**: Decay is evaluated strictly against turn increments, never system wall-clock time.\n- **Channel Partitioning**: Decay speeds mirror data reliability, prioritizing validated evidence over ephemeral tool output.\n- **State Serialization**: Session states export to portable JSON snapshots for cross-run reproducibility.\n\n### Verification Flow\n1. Register memory items via `harness memory register`.\n2. Advance conversation turns via `harness memory step`.\n3. Inspect active vs soft-evicted items via `harness memory working-set`.\n4. Run comparative decay benchmarks via `harness memory benchmark`.\n\n---\n\n## Operational Workflow\n\n```bash\n# 1. Register foundational instruction (immune to eviction)\nharness memory register --key \"rule-1\" --content \"Preserve docstrings\" --channel instruction --foundational\n\n# 2. Register ephemeral tool output (fast decay)\nharness memory register --key \"temp-grep\" --content \"Grep returned 4 lines\" --channel tool_output --stability 2.0\n\n# 3. Advance turns\nharness memory step --turns 5\n\n# 4. Recall and reinforce an item\nharness memory recall \"rule-1\"\n\n# 5. Inspect working set (active only)\nharness memory working-set --ranked\n\n# 6. Inspect complete history (including soft-evicted items)\nharness memory working-set --include-evicted\n```\n\n---\n\n## Mandatory Checkpoints\n\n- [ ] **Deterministic Turn Clock**: Verify that decay occurs only upon explicit `step_turn()`, never wall-clock time.\n- [ ] **Foundational Immunity**: Verify that items with `is_foundational=True` remain in `working_set()` regardless of turn count.\n- [ ] **Soft Demotion Invariant**: Verify that soft-evicted items remain retrievable via `include_evicted=True`.\n\n---\n\n## Anti-Patterns\n\n- **Recency-Only Purging** — Evicting frequently recalled foundational facts simply because they were not touched in the most recent turn.\n- **Hard Item Deletion** — Permanently dropping items from session history upon eviction instead of setting `item.evicted = True`.\n- **Wall-Clock Decay Coupling** — Relying on real-time system timestamps instead of logical conversation turn steps for deterministic reproducibility.\n- **Unweighted Decay Rates** — Subjecting raw tool output and system instructions to identical decay schedules.\n\n---\n\n## Related Skills & Docs\n\n- [Context Type System](..\u002Fcontext-type-system\u002FSKILL.md)\n- [OKF Memory Governor](..\u002Fokf-memory-governor\u002FSKILL.md)\n- [Learning Core Lifecycle Narrative](..\u002F..\u002F..\u002Fdocs\u002Fexplanation\u002Flearning-core-lifecycle.md)\n- [Memory Architecture Explanation](..\u002F..\u002F..\u002Fdocs\u002Fexplanation\u002Fmemory-architecture.md)\n","# Ebbinghaus Memory Governor\n\n## Overview\n\nThe Ebbinghaus Memory Governor provides mathematical forgetting curve retention management for agent working memory. By modeling non-linear stability growth upon repeated recall, foundational instructions remain protected indefinitely while ephemeral tool outputs decay and soft-evict predictably.\n\n```\n┌─────────────────────────────────────────────────────────────┐\n│                 Turn Advance: step_turn()                   │\n└──────────────────────────────┬──────────────────────────────┘\n                               │\n       ┌───────────────────────┴───────────────────────┐\n       ▼                                               ▼\n┌──────────────────────────────┐        ┌──────────────────────────────┐\n│ is_foundational = True       │        │ is_foundational = False      │\n│ (Immune to Eviction)         │        │ R(t) = exp(-Δt \u002F (S \u002F m))    │\n└──────────────────────────────┘        └──────────────┬───────────────┘\n                                                       │\n                                        ┌──────────────┴───────────────┐\n                                        ▼                              ▼\n                         ┌─────────────────────────────┐ ┌─────────────────────────────┐\n                         │ R(t) >= 0.20                │ │ R(t) \u003C 0.20                 │\n                         │ ACTIVE IN WORKING SET       │ │ SOFT EVICTION               │\n                         │ Included in recall & prompt │ │ item.evicted = True         │\n                         │ S_new = S * (1 + ln(1 + n)) │ │ Preserved in item history   │\n                         └─────────────────────────────┘ └─────────────────────────────┘\n```\n\n---\n\n## Verified Soft-Demotion Semantics\n\nForgetting in this engine is **soft eviction (demotion from active working set), NOT permanent deletion**:\n1. **Turn-Based Retention Calculus**:\n   At each dialogue step $\\Delta t$, retention is computed as:\n   $$R(t) = \\exp\\left(-\\frac{\\Delta t}{S \u002F m_{\\text{channel}}}\\right)$$\n2. **Channel Decay Multipliers**:\n   Channel multipliers $m_{\\text{channel}}$ scale the rate of decay across 5 semantic channels (aligned with [Context Type System](..\u002Fcontext-type-system\u002FSKILL.md)):\n   - `instruction`: $0.25\\times$ (ultra-slow decay)\n   - `foundational`: $0.35\\times$ (slow decay)\n   - `evidence`: $0.70\\times$ (moderate decay)\n   - `memory`: $1.00\\times$ (standard baseline)\n   - `tool_output`: $1.75\\times$ (rapid decay)\n3. **Soft Eviction (`item.evicted = True`)**:\n   When $R(t) \u003C 0.20$, the item is marked as `evicted = True`. It is excluded from active `working_set()` and `recall()`, but **remains in memory storage** (`engine.items`) and is fully preserved in exported snapshot files and recoverable via `memory_query_working_set(include_evicted=True)`.\n4. **Foundational Immunity**:\n   Items with `is_foundational=True` bypass the retention check and are **never evicted**.\n5. **Non-Linear Stability Reinforcement**:\n   Recalling an active item increases its stability monotonically:\n   $$S_{\\text{new}} = S_{\\text{old}} \\cdot (1 + \\ln(1 + n_{\\text{recalls}}))$$\n\n---\n\n## Visual Brief\n\n### Architecture\n- **Logical Turn Clock**: Decay is evaluated strictly against turn increments, never system wall-clock time.\n- **Channel Partitioning**: Decay speeds mirror data reliability, prioritizing validated evidence over ephemeral tool output.\n- **State Serialization**: Session states export to portable JSON snapshots for cross-run reproducibility.\n\n### Verification Flow\n1. Register memory items via `harness memory register`.\n2. Advance conversation turns via `harness memory step`.\n3. Inspect active vs soft-evicted items via `harness memory working-set`.\n4. Run comparative decay benchmarks via `harness memory benchmark`.\n\n---\n\n## Operational Workflow\n\n```bash\n# 1. Register foundational instruction (immune to eviction)\nharness memory register --key \"rule-1\" --content \"Preserve docstrings\" --channel instruction --foundational\n\n# 2. Register ephemeral tool output (fast decay)\nharness memory register --key \"temp-grep\" --content \"Grep returned 4 lines\" --channel tool_output --stability 2.0\n\n# 3. Advance turns\nharness memory step --turns 5\n\n# 4. Recall and reinforce an item\nharness memory recall \"rule-1\"\n\n# 5. Inspect working set (active only)\nharness memory working-set --ranked\n\n# 6. Inspect complete history (including soft-evicted items)\nharness memory working-set --include-evicted\n```\n\n---\n\n## Mandatory Checkpoints\n\n- [ ] **Deterministic Turn Clock**: Verify that decay occurs only upon explicit `step_turn()`, never wall-clock time.\n- [ ] **Foundational Immunity**: Verify that items with `is_foundational=True` remain in `working_set()` regardless of turn count.\n- [ ] **Soft Demotion Invariant**: Verify that soft-evicted items remain retrievable via `include_evicted=True`.\n\n---\n\n## Anti-Patterns\n\n- **Recency-Only Purging** — Evicting frequently recalled foundational facts simply because they were not touched in the most recent turn.\n- **Hard Item Deletion** — Permanently dropping items from session history upon eviction instead of setting `item.evicted = True`.\n- **Wall-Clock Decay Coupling** — Relying on real-time system timestamps instead of logical conversation turn steps for deterministic reproducibility.\n- **Unweighted Decay Rates** — Subjecting raw tool output and system instructions to identical decay schedules.\n\n---\n\n## Related Skills & Docs\n\n- [Context Type System](..\u002Fcontext-type-system\u002FSKILL.md)\n- [OKF Memory Governor](..\u002Fokf-memory-governor\u002FSKILL.md)\n- [Learning Core Lifecycle Narrative](..\u002F..\u002F..\u002Fdocs\u002Fexplanation\u002Flearning-core-lifecycle.md)\n- [Memory Architecture Explanation](..\u002F..\u002F..\u002Fdocs\u002Fexplanation\u002Fmemory-architecture.md)\n",{"name":5,"cluster":24,"description":7},"memory_and_epistemics","main","eff3b00e36d1d233ad4a4389605c82fbfa0326d3",".agents\u002Fskills\u002Febbinghaus-memory-governor","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness","https:\u002F\u002Fgithub.com\u002FSpectreDeath","I'm here to manage stress so I wouldn't expect earth shattering break throughs I'm just an enthusiast that likes making stuff. ","2026-11-15 05:32:58",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add SpectreDeath\u002FBrain-Harness --skill ebbinghaus-memory-governor",{"tool":38,"command":39},"bunx","bunx skills add SpectreDeath\u002FBrain-Harness --skill ebbinghaus-memory-governor",{"tool":41,"command":42},"pnpm","pnpm dlx skills add SpectreDeath\u002FBrain-Harness --skill ebbinghaus-memory-governor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Febbinghaus-memory-governor\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"CARD.md","REFERENCE","参考文档",2937,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Febbinghaus-memory-governor\u002FCARD.md",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7E0W6FR68J2N9CXCZTAQJFX","ui-behavior-primitive-architect","Architect, audit, and verify zero-dependency headless UI behavior primitives, WebMCP agent bridges, WAI-ARIA\u002FSSR\u002FRTL tri-modal checks, and framework expert routing. Do not use for static CSS theme styling or backend database migrations.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fui-behavior-primitive-architect\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7E0VZ7JQNW34G271DENFGYP","trustgraph-ontology-governor","Govern knowledge graphs, SHACL-AF triple policies, OntologyRAG subclass validation, PROV-O dual named graphs, and Laya entropy decision scoring. Do not use for relational SQL queries or generic web scraping.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftrustgraph-ontology-governor\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7E0VQ6Z7R45Q8QAZ4MT39EK","shim-harness-governor","Govern universal CLI agent loops, 4-tier tool permissions, ancestor-symlink workspace sandboxes, deterministic-first command routing, collision-safe MCP namespacing, and layered skill loading. Do not use for static UI styling or external SQL analytics.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fshim-harness-governor\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7E0VC18NMP1QBSRJ3TPQ7MB","graphiti-zep-memory-governor","Govern bi-temporal knowledge graphs with Graphiti future-edge clamping, MinHash\u002FLSH entity dedup, RRF\u002FMMR reranking, and Zep typed ontologies. Do not use for static SQL joins or generic web crawling.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgraphiti-zep-memory-governor\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7E0V12ABE1RW3ZRCST8VH5Z","agora-mcp-workbench-architect","Architect, audit, and orchestrate Agora Workbench MCP servers, loopback sidecars, unified state graphs, gateway\u002Fdispatcher connectors, and policy-enforced data lakes. Do not use for static frontend CSS styling or non-MCP desktop GUI automation.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagora-mcp-workbench-architect\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7BFYG6QT3484VC57TZ19V7P","skill-eval-assurance-runner","Evaluate and assure agent skills using small-N Wilson confidence intervals, unbiased pass^k reliability, deterministic trajectory graders, preflight boundary honesty, and sealed digest verification. Do not use for subjective prose review or unconstrained production deployment.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-eval-assurance-runner\u002FSKILL.md",[],[]]