Questlog

@ghostpaw/questlog

npm CI site runtime deps MCP Registry node license

Agent tasks as quests that finish only with a written outcome.

npm install @ghostpaw/questlog

A unified task and calendar model for Node.js, built on SQLite.

Questlog treats tasks, events, deadlines, recurring commitments, and loose intake as one coherent data model instead of separate systems. It ships as a single prebundled blob with zero runtime dependencies, designed for two audiences at once: human developers working directly in code, and LLM agents operating through a structured tool facade.

MCP server

Every client below starts the same stdio server: npx -y @ghostpaw/questlog mcp. Data lives in ~/.ghostpaw/questlog.db unless the GHOSTPAW_QUESTLOG_DB environment variable (absolute path) or --db <path> says otherwise.

Claude Code

claude mcp add ghostpaw-questlog -- npx -y @ghostpaw/questlog mcp

or as a plugin, which also installs the skill:

/plugin marketplace add GhostPawJS/questlog
/plugin install ghostpaw-questlog@ghostpaw-questlog

Codex CLI (~/.codex/config.toml)

[mcp_servers.ghostpaw-questlog]
command = "npx"
args = ["-y", "@ghostpaw/questlog", "mcp"]

Cursor (.cursor/mcp.json), Claude Desktop (claude_desktop_config.json) or a project .mcp.json:

{
  "mcpServers": {
    "ghostpaw-questlog": {
      "command": "npx",
      "args": ["-y", "@ghostpaw/questlog", "mcp"]
    }
  }
}

Claude Desktop users can also install server.mcpb from the latest GitHub release. A Dockerfile is included for container hosts: docker build -t ghostpaw-questlog . && docker run -i --rm -v questlog:/data ghostpaw-questlog.

The server speaks MCP 2026-07-28 (stateless, server/discover) and the initialize-based revisions 2025-11-25, 2025-06-18, 2025-03-26 and 2024-11-05.

CLI

npx -y @ghostpaw/questlog tools
npx -y @ghostpaw/questlog call capture_rumor '{"title":"Review release notes"}'
npx -y @ghostpaw/questlog call search_questlog '{"query":"release notes"}'

Install globally for the ghostpaw-questlog binary: npm i -g @ghostpaw/questlog. ghostpaw-questlog mcp starts the stdio server.

Agent Skill

SKILL.md (repo root) and skills/questlog/SKILL.md follow the Agent Skills format and ship in the npm package. Copy skills/questlog/ into your agent's skills folder, or print it:

npx -y @ghostpaw/questlog skill > SKILL.md

Install

npm install @ghostpaw/questlog

Requires Node.js 24+ (uses the built-in node:sqlite module).

Quick Start

import { DatabaseSync } from 'node:sqlite';
import { initQuestlogTables, read, write } from '@ghostpaw/questlog';

const db = new DatabaseSync(':memory:');
initQuestlogTables(db);

// Capture incoming work as a rumor before committing to shape
const rumor = write.captureRumor(db, {
  title: 'Legal says the vendor terms changed',
  details: 'Need to understand pricing delta and termination clause.',
});

// Settle the rumor into real work once the shape is clear
write.settleRumor(db, rumor.id, {
  settledAt: Date.now(),
  questline: {
    title: 'Vendor Renewal',
    description: 'Commercial, legal, and approval work.',
  },
  quests: [
    { title: 'Collect redlines', objective: 'Obtain the latest legal markup.' },
    { title: 'Review pricing delta', objective: 'Compare current vs. proposed cost.' },
  ],
});

// Drive the day from derived views, not from memory
const available = read.listAvailableQuests(db);
const dueSoon = read.listDueSoonQuests(db, 7 * 24 * 60 * 60 * 1000);
const results = read.searchQuestlog(db, 'vendor');

The Model

Seven concepts, strict separation of concerns:

Concept	Purpose
Rumor	Incoming signal that may or may not become real work
Questline	Shared context and rollup for a group of related quests
Quest	One concrete commitment with lifecycle, timing, and outcome
Repeatable Quest	Recurring template that spawns fresh quests on a schedule
Unlock	Hard prerequisite: quest B stays blocked until quest A succeeds
Reward	Descriptive outcome attached to completed work, with a claim lifecycle
Tag	Cross-cutting label for filtering and reporting

The unified model means one entity type covers every temporal intention:

What it looks like	What it actually is
A todo item	A quest with no temporal metadata
A deadline	A quest with dueAt
A calendar event	A quest with scheduledStartAt and scheduledEndAt
A recurring commitment	A repeatable quest with an RRULE
A completed action	A quest resolved via finishQuest

State is derived, not toggled. A quest's availability comes from its lifecycle, timing fields, and unlock graph — computed at read time, never stored as a status flag.

Lifecycle at a glance

Questlog computes WoW-style markers on every read. They change as work moves through its lifecycle:

 

Intake

$\color{Goldenrod}{\textsf{❗}}$	Legal says the vendor terms changed	rumor · open
	↓   settle into questline + quests

Quest progression

$\color{Goldenrod}{\textsf{❗}}$	Review pricing delta	open · available
$\color{Gray}{\textsf{❓}}$	Review pricing delta	in progress
$\color{Goldenrod}{\textsf{❓}}$	Review pricing delta	done · reward unclaimed
✓	Review pricing delta	done · reward claimed

Other markers

$\color{CornflowerBlue}{\textsf{❗}}$	Weekly standup notes	repeatable · due
$\color{Gray}{\textsf{❗}}$	Plan Q3 roadmap	open · deferred
$\color{Gray}{\textsf{❓}}$	Obtain finance approval	open · blocked

 

Marker IDs are semantic strings (attention.available, progress.complete, ...) computed at read time, never stored. The markers namespace maps each to its symbol, color, label, and CSS class for consistent rendering across HTML, TTY, and plain text.

Two Audiences

Human developers

Use the read and write namespaces for direct-code access to every domain operation:

import { read, write } from '@ghostpaw/questlog';

write.createQuest(db, { title: 'Ship release notes', objective: 'Draft and publish.' });
write.startQuest(db, questId);
write.finishQuest(db, questId, 'Published to blog and changelog.');

const blocked = read.listBlockedQuests(db);
const overdue = read.listOverdueQuests(db);

See HUMAN.md for the full human-facing guide with worked examples.

LLM agents

Use the tools, skills, and soul namespaces for a structured runtime surface designed to minimize LLM cognitive load:

import { tools, skills, soul } from '@ghostpaw/questlog';

// 12 intent-shaped tools with JSON Schema inputs and structured results
const allTools = tools.questlogTools;
const searchTool = tools.getQuestlogToolByName('search_questlog')!;
const result = searchTool.handler(db, { query: 'vendor', mode: 'browse' });

// 25 reusable workflow skills for common multi-step scenarios
const allSkills = skills.questlogSkills;

// Thinking foundation for system prompts
const prompt = soul.renderQuestlogSoulPromptFoundation();

Every tool returns a discriminated result with outcome: 'success' | 'no_op' | 'needs_clarification' | 'error', structured entities, next-step hints, and actionable recovery advice. No thrown exceptions to parse, no ambiguous prose.

See LLM.md for the full AI-facing guide covering soul, tools, and skills.

Tools

Twelve tools shaped around operator intent, not raw storage operations:

Tool	What it does
search_questlog	Cross-entity full-text search
review_questlog	Filtered list views (available, overdue, due soon, ...)
inspect_questlog_item	Detailed inspection of any single entity
capture_rumor	Record incoming work before committing to shape
shape_work	Create quests, questlines, settle rumors into structure
plan_quest	Set timing: due dates, defer dates, scheduled windows
run_quest	Start, finish, abandon, log effort
organize_work	Move quests between questlines, manage questline lifecycle
manage_repeatable	Create and maintain recurring quest templates
tag_work	Classify quests and repeatables with tags
reward_work	Attach, update, claim, or remove rewards
retire_work	Soft-delete or archive things that should leave the active surface

Each tool exports runtime metadata — name, description, JSON Schema, input descriptions, side-effect level — so agent harnesses can wire them without reading docs.

The run_quest tool refuses to start a quest with unmet unlock prerequisites and returns the blocking quests with inspection hints. Set force: true to start anyway with a warning. The library startQuest function remains permissive.

Key Properties

• Zero runtime dependencies. Only node:sqlite (built into Node 24+).
• Single prebundled blob. One ESM + one CJS entry in dist/. No subpath exports, no code splitting.
• Pure SQLite storage. FTS5 full-text search, CHECK-constrained state transitions, trigger-maintained indexes. Bring your own DatabaseSync instance.
• Derived state. Availability, blocking, deferral, overdue, and markers are computed at read time from fields and relationships, never stored as flags.
• Intention-shaped writes. captureRumor, settleRumor, startQuest, finishQuest, abandonQuest — operations that say what happened, not generic CRUD.
• RFC 5545 recurrence. Standard RRULE strings for recurring work. No custom recurrence format.
• WoW-style markers. Semantic marker IDs (attention.available, progress.complete, ...) computed on every read, renderable to any channel.
• Colocated tests. Every non-type module has a colocated .test.ts file. The behavior described in docs is backed by executable coverage.

Performance

Measured with npm run bench on Node 24.14.0, Linux, Intel Xeon (shared cloud vCPU), 10,000 quests in a file-backed database:

Operation	p50	p95
search_questlog (tool)	0.06 ms	0.07 ms
MCP tools/call search, stdio framing included	0.07 ms	0.08 ms
read.searchQuestlog, one matching quest	0.07 ms	0.08 ms
read.searchQuestlog, all 10,000 quests matching	26.6 ms	41.9 ms
write.createQuest	0.22 ms	0.69 ms

The library search returns every match with a highlighted snippet, so a query that matches the whole log pays for building all of those rows. Cold start (process spawn to first response, median) is about 30 ms for --version and the MCP server.

Package Surface

import {
  initQuestlogTables,  // schema setup
  read,                // all query functions
  write,               // all mutation functions
  tools,               // LLM tool definitions + registry
  skills,              // LLM workflow skills + registry
  soul,                // thinking foundation for system prompts
  markers,             // marker derivation and lookup
} from '@ghostpaw/questlog';

All domain types are also available at the root for TypeScript consumers:

import type {
  QuestlogDb,
  QuestState,
  QuestDetail,
  CreateQuestInput,
  QuestlogSearchResult,
  QuestlogToolDefinition,
  QuestlogSkill,
  QuestlogSoul,
} from '@ghostpaw/questlog';

Documentation

Document	Audience
HUMAN.md	Human developers using the low-level read/write API
LLM.md	Agent builders wiring tools, skills, and soul into LLM systems
docs/README.md	Architecture overview: model, invariants, lifecycle, markers
docs/entities/	Per-entity manuals with exact public API listings

Development

npm install
npm test            # node:test runner
npm run typecheck   # tsc --noEmit
npm run lint        # biome check
npm run build       # ESM + CJS + declarations via tsup

The repo is pinned to Node 24.14.0 via .nvmrc / .node-version / .tool-versions / mise.toml / Volta. Use whichever version manager you prefer.

Support

If this package helps your project, consider sponsoring its maintenance:

GitHub Sponsors

---

Anonyfox • MIT License