Chalk Labs
Need help deploying quest-management?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/engramist-quest-management
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
quest-management- Description
- None
- License
- Apache-2.0
- Instructions
- 55 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- missing YAML frontmatter
- name: missing
- description: missing
Files (1)
- SKILL.md
SKILL.md (first lines)
# Quest Management SideQuests organizes knowledge into Quests — focused contexts for projects or workstreams. ## Main Quests A Main Quest is automatically created for each project context. For developers, this maps to a git repository. For non-dev users, the Brain uses semantic routing to figure out which Quest a conversation belongs to. ## Side Quests When a conversation shifts to a distinct tangent worth tracking separately, **ALWAYS offer to create a Side Quest:** ``` branch_quest(name="<tangent name>", purpose="<what this is about>") ``` **Important:** Always offer this — never create a Side Quest without the user's agreement. Say something like: "This seems like a separate topic from what we've been discussing. Want me to branch this into its own Side Quest so we can track it separately?" ## Completing Quests **When a project wraps up, you MUST call `complete_quest`:** ``` complete_quest(quest_id="<quest_id>") ``` Completed quests are excluded from active search results but remain available for cross-quest learning — the Brain can surface relevant patterns from past projects when you start something similar. ## Setting the Quest explicitly If the Brain routes a conversation to the wrong Quest, or you want to start a specific project context: ``` set_quest(session_id="<session>", quest_name="<project name>") ``` This overrides automatic routing and locks the session to the named Quest. ## Switching Context with Memory When switching to a different quest or returning to a project after time away, ALWAYS call `diff_since` to see what changed: ``` diff_since(since_iso="<last session timestamp>") ``` This shows nodes created, updated, or deprecated since your last visit — crucial for catching up on changes made in other conversations or by other agents. If you don't know the last session timestamp, use `reconstruct_timeline` to see recent activity: ``` reconstruct_timeline(quest_id="<quest>", limit=20) ```
From engramist/hippocampy, Apache-2.0.
More from engramist/hippocampy
- 0.476score
campy-diagnose
engramist
Campy-enhanced diagnosis loop for hard bugs and performance regressions.
SkillCFreshness: CClaude Code +9 - 0.474score
brief
engramist
Deep context briefing from Campy's knowledge graph.
SkillCFreshness: CClaude Code +9 - 0.474score
graph-expert
engramist
Graph database expertise and architectural consulting.
SkillCFreshness: CClaude Code +9 - 0.474score
learn
engramist
Teach Campy a new pattern, procedure, or lesson.
SkillCFreshness: CClaude Code +9 - 0.471score
campy-handoff
engramist
Campy-enhanced handoff that writes a transfer note and persists it to Campy's graph.
SkillCFreshness: CClaude Code +9 - 0.471score
campy-improve-architecture
engramist
Campy-enhanced architecture deepening skill.
SkillCFreshness: CClaude Code +9 - 0.471score
campy-tdd
engramist
Campy-enhanced test-driven development with red-green-refactor loop.
SkillCFreshness: CClaude Code +9 - 0.471score
campy-grill
engramist
Campy-enhanced grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md…
SkillCFreshness: CClaude Code +9 - 0.304score
campy-memory
engramist
No description from the publisher yet.
SkillAFreshness: AClaude Code +9 - 0.251score
recall
engramist
No description from the publisher yet.
SkillCFreshness: CClaude Code +9 - 0.251score
session-start
engramist
No description from the publisher yet.
SkillCFreshness: CClaude Code +9 - 0.251score
status
engramist
No description from the publisher yet.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- May 22, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/engramist/hippocampy
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from engramist
- 0.476score
campy-diagnose
engramist
Campy-enhanced diagnosis loop for hard bugs and performance regressions.
SkillCFreshness: CClaude Code +9 - 0.474score
brief
engramist
Deep context briefing from Campy's knowledge graph.
SkillCFreshness: CClaude Code +9 - 0.474score
graph-expert
engramist
Graph database expertise and architectural consulting.
SkillCFreshness: CClaude Code +9 - 0.474score
learn
engramist
Teach Campy a new pattern, procedure, or lesson.
SkillCFreshness: CClaude Code +9 - 0.471score
campy-handoff
engramist
Campy-enhanced handoff that writes a transfer note and persists it to Campy's graph.
SkillCFreshness: CClaude Code +9 - 0.471score
campy-improve-architecture
engramist
Campy-enhanced architecture deepening skill.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get quest-management running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
quest-management skill. Agent Mart. https://agentmart.dev/skills/engramist-quest-management (last updated 2026-10-24)