horizon-track — Claude Code skill: what it does, how to install
Tracks long-term objectives across multiple sessions, stores milestones in persistent memory, and flags project drift.
npx skills add ruvnet/ruflo --skill horizon-track -a claude-codeWhat horizon-track does
This skill coordinates objectives that span days or weeks, including migrations, research programs, or large features. It breaks an objective down into 3 to 7 milestones, sets a deadline, and maintains persistent state across the horizons, horizon-sessions, and horizon-learnings memory namespaces.
At the start of every session, the agent retrieves the current horizon state via ruflo memory tools, inspects milestone statuses, and assesses drift against deadlines. Before ending the session, it logs accomplishments, blockers, and remaining effort estimates. When a milestone wraps up, extracted patterns move to persistent intelligence storage.
The skill strictly depends on tools exposed by the ruflo-core MCP plugin. Without that server running, persistent memory queries will fail immediately.
What it helps with
- persist multi-session project progress across agent restarts
- break large migration efforts into verifiable milestone checkpoints
- detect schedule drift and unplanned scope growth early
- record blockers and extracted patterns into persistent memory
Example prompts for the agent
- Start tracking the objective using horizon-track auth-migration
- Check milestone progress for horizon-track payments-v2 and record session results
- Review scope drift and remaining effort for horizon-track refactor-core
How to install horizon-track
1Skills CLI (Vercel)
npx skills add ruvnet/ruflo --skill horizon-track -a claude-code2Manually: put the files in place
~/.claude/skills/horizon-track/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/horizon-track/
1Skills CLI (Vercel)
npx skills add ruvnet/ruflo --skill horizon-track -a codex2Manually: put the files in place
.agents/skills/horizon-track/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ruvnet/ruflo --skill horizon-track -a cursor2Manually: put the files in place
.cursor/skills/horizon-track/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ruvnet/ruflo horizon-track2Manually: put the files in place
.github/skills/horizon-track/SKILL.md1Skills CLI (Vercel)
npx skills add ruvnet/ruflo --skill horizon-track -a gemini-cli2Platform CLI
gemini skills install https://github.com/ruvnet/ruflo --path plugins/ruflo-goals/skills/horizon-trackManually: put the files in place
.devin/skills/horizon-track/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add ruvnet/ruflo --skill horizon-track -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set104
The whole set →Similar
Questions about horizon-track
How do I install horizon-track in Claude Code?
Run npx skills add ruvnet/ruflo --skill horizon-track -a claude-code.
What does horizon-track do?
It tracks multi-day or multi-week goals across sessions. The skill structures goals into milestones, logs check-ins, and warns you if progress drops behind schedule.
What tools does horizon-track require?
It relies on memory tools provided by the ruflo-core MCP plugin alongside standard Bash, Read, and Write capabilities.
Source text
SKILL.md · MIT
---
name: horizon-track
description: Track long-horizon objectives across multiple sessions with milestone checkpoints, progress persistence, and drift detection
argument-hint: "<objective-name>"
allowed-tools: mcp__plugin_ruflo-core_ruflo__memory_store mcp__plugin_ruflo-core_ruflo__memory_search mcp__plugin_ruflo-core_ruflo__memory_list mcp__plugin_ruflo-core_ruflo__memory_retrieve mcp__plugin_ruflo-core_ruflo__task_list mcp__plugin_ruflo-core_ruflo__task_summary mcp__plugin_ruflo-core_ruflo__progress_check mcp__plugin_ruflo-core_ruflo__progress_summary mcp__plugin_ruflo-core_ruflo__agentdb_hierarchical-store mcp__plugin_ruflo-core_ruflo__agentdb_hierarchical-recall mcp__plugin_ruflo-core_ruflo__hooks_intelligence_pattern-store mcp__plugin_ruflo-core_ruflo__session_save mcp__plugin_ruflo-core_ruflo__session_restore Bash Read Write
---
# Horizon Track
Track long-running objectives that span multiple sessions, days, or weeks.
## When to use
When an objective is too large for a single session — multi-week features, research programs, migration projects, or any work that requires persistent progress tracking across conversations.
## Steps
1. **Initialize horizon** — define the objective, target date, and 3-7 milestones
2. **Store horizon** — call `mcp__plugin_ruflo-core_ruflo__memory_store` with namespace `horizons` and key `horizon-[name]`:
```json
{
"objective": "...",
"created": "2026-04-28",
"targetDate": "2026-05-15",
"milestones": [
{"id": "m1", "name": "...", "criteria": "...", "status": "pending"},
{"id": "m2", "name": "...", "criteria": "...", "status": "pending"}
],
"currentMilestone": "m1",
"sessions": []
}
```
3. **Session check-in** — at the start of each session:
- Recall horizon: `mcp__plugin_ruflo-core_ruflo__memory_retrieve` key `horizon-[name]` namespace `horizons`
- Review milestone status
- Assess drift (are we still on track?)
- Plan this session's contribution
4. **Work and record** — as work progresses:
- Update milestone status
- Record session summary
- Store intermediate findings
5. **Session check-out** — at the end of each session:
- Update horizon state in memory
- Record what was accomplished
- Note blockers or scope changes
- Estimate remaining effort
6. **Milestone completion** — when a milestone is done:
- Verify completion criteria met
- Store learned patterns via `mcp__plugin_ruflo-core_ruflo__hooks_intelligence_pattern-store`
- Advance to next milestone
7. **Drift detection** — flag when:
- Progress rate suggests target date will be missed
- Scope has grown beyond original definition
- Dependencies have changed
- Approach needs fundamental rethinking
## Memory namespaces
- `horizons` — active horizon definitions and state
- `horizon-sessions` — per-session summaries keyed by `[horizon]-[date]`
- `horizon-learnings` — patterns and insights discovered during the horizon
© ruvnet · MIT · ruvnet/ruflo