agentleFS
msking18msking18/agent-memory-mcp/skills/agent-memory/SKILL.md

agent-memory

Skill4 starsChanged 9 days agoMITView on GitHub

Guide and workflow reference for agent-memory-mcp v3.1 — per-project SQLite + FTS5 architectural memory, centralized global knowledge graph, two-tier dead-end taxonomy, token budgeting middleware, and legacy .ag-memory.json JIT migration.

38 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use observability, data-analysis and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • OpenAISkill

    observability

    Vercel Observability expert guidance — Drains (logs, traces, speed insights, web analytics), Web Analytics, Speed Insights, runtime logs, custom events, OpenTelemetry integration, and monitoring dashboards. Use when instrumenting, debugging, or optimizing application performance and user experience on Vercel.

    Also in 4 projects that use this

  • shanggqmSkill

    data-analysis

    数据分析技能,提供结构化的数据查询、统计分析和报告生成工作流。当用户需要查询数据库、进行数据统计分析、生成分析报告时使用。按规范输出原始数据、计算结果、Markdown报告和HTML可视化报告。

    Also in 3 projects that use this

  • Microsoft AzureSkill

    skill-authoring

    Write Agent Skills that comply with the agentskills.io specification. WHEN: "create a skill", "new skill", "write a skill", "skill template", "skill structure", "review skill", "skill PR", "skill compliance", "SKILL.md format", "skill frontmatter", "skill best practices". DO NOT USE FOR: general documentation. INVOKES: vally CLI.

    Also in 3 projects that use this

  • VercelSkill

    technical-writing

    Write, edit, review, or audit user-facing documentation for the eve repository. Use for changes under docs/, documentation tied to eve APIs or CLI behavior, docs work based on Slack or support feedback, and requests to make eve docs clearer, more natural, or less AI-patterned while verifying claims against current source, tests, CLI help, public releases, and repository conventions.

    Also in 3 projects that use this

  • JetBrainsSkill

    webapp-testing

    Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

    Also in 4 projects that use this

  • AnthropicSkill

    pdf

    Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 33 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When initializing a new project workspace, save all 3 core architectural nodes in one atomic transaction:

    line 43

“Common” is measured: kept by at least 6 in 10 of the 33 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Agent Memory (agent-memory-mcp v3.1)

agent-memory-mcp provides persistent, ACID-safe, full-text searchable memory for AI coding agents. Backed by Node 22.5+/24+ native node:sqlite (WAL + FTS5), it features per-project databases, a centralized cross-project global knowledge graph, a two-tier anti-loop dead-end registry, and token budgeting middleware.

Storage Architecture

  • Per-Project Live Stores: ~/.ag-memory-mcp/stores/<project-slug>-<hash>.db (keeps repository trees 100% clean).
  • Central Global Knowledge Graph: ~/.ag-memory-mcp/global.db (cross-project patterns, library quirks, and token audit logs).
  • Configuration: ~/.ag-memory-mcp/config.json (or AG_MEMORY_MAX_RESPONSE_TOKENS environment variable).
  • Zero-Loss JIT Migration: Automatically detects, verifies, and archives legacy <project_path>/.ag-memory.json (v2.0) to ~/.ag-memory-mcp/backups/.

Tool Quick Reference (15 Tools)

Project-Scoped Memory Tools (1–10)

ToolModeBest Used For
check_memory_statusRead-only1-shot check returning initialization state, architecture TOC, dead-end count, and top 5 timeline logs.
get_session_timelineRead-onlyChronological feed filterable by category (session, architecture, decision, note, all), tag, and since.
save_project_memoryWrite/UpsertSingle or atomic batch (entries: [...]) save; auto-upserts matching id or slug while archiving prior revisions.
search_project_memoryRead-onlyWeighted FTS5 BM25 search across title, tags, files, and summary (plus matching dead-ends) with snippets.
read_memory_nodeRead-onlyReads single id or batch ids: [...] (supports slugs like "tech-stack" or "g-..." global IDs), checking files[] disk mtime for staleness.
update_memory_nodeWritePartial update to title, summary, tags, category, or files with automatic revision backup.
delete_memory_nodeWriteSoft-archives obsolete memories (hard_delete: false default) or permanently deletes (hard_delete: true).
record_dead_endWriteLogs { error_pattern, attempted_solution, root_cause, files, kind, constraints } (error_loop vs architectural).
check_dead_endsRead-onlySearches recorded dead-ends by error message, keyword, or file_path, filterable by kind.
get_file_memoriesRead-onlyReturns all memories and dead-ends anchored to file_paths: [...] (or parent directories) before refactoring.

Global Knowledge & Taxonomy Tools (11–15)

ToolModeBest Used For
save_global_knowledgeWriteSaves cross-project patterns or library quirks to global.db (auto-generates g- prefixed IDs).
search_global_knowledgeRead-onlyBM25 ranked FTS5 search across global patterns, filterable by tech_stack and category.
promote_to_globalWritePromotes a validated project-specific memory node into the machine-wide global knowledge graph.
reopen_dead_endWriteReopens a past dead-end when external constraints, library updates, or requirements change.
get_token_metricsRead-onlyRetrieves machine-wide token efficiency statistics and audit logs from global.db.

Canonical Bootstrap Pattern (Single Atomic Call)

When initializing a new project workspace, save all 3 core architectural nodes in one atomic transaction:

{
  "project_path": "C:/Projects/MyApp",
  "entries": [
    {
      "slug": "tech-stack",
      "title": "Tech Stack & Ecosystem",
      "category": "architecture",
      "tags": ["architecture", "stack"],
      "summary": "..."
    },
    {
      "slug": "project-structure",
      "title": "Project Structure & Architecture",
      "category": "architecture",
      "tags": ["architecture", "structure"],
      "files": ["src/index.ts"],
      "summary": "..."
    },
    {
      "slug": "build-run",
      "title": "Build & Run Instructions",
      "category": "architecture",
      "tags": ["architecture", "build"],
      "files": ["package.json"],
      "summary": "..."
    }
  ]
}

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.