Task Router Skill
Task Router
Maintain persistent focus on active work across compactions and session restarts. Use when starting a multi-step project, when resuming after compaction, when the user says "we're working on X", or when you notice you've lost track of what was being done. Also use proactively at session start to check if there's unfinished work. Prevents the agent from forgetting mid-project context, drifting between topics, or asking "what were we doing?" after a compaction.
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
SkillHub CLI
skillhub install crewhaus/focus-trackerInspect the source and compatibility requirements, then follow its installation steps.
Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.
Maintain a FOCUS.md file in the workspace root as persistent working state.
FOCUS-LOG.md and clear FOCUS.md# FOCUS — [Project Name]
**Started:** YYYY-MM-DD HH:MM UTC
**Status:** active | paused | blocked
**Context:** One-line summary of WHY we're doing this
## Objective
What we're trying to accomplish (1-3 sentences max)
## Plan
Numbered steps. Check off as completed.
- [x] Step 1 — done
- [ ] Step 2 — in progress (note current state)
- [ ] Step 3 — next
## Active State
What's happening RIGHT NOW. What was the last thing done, what's the next action.
This is the most important section — it's the "resume point" after compaction.
## Blockers
Anything waiting on the user, external systems, or decisions.
## Sub-Agents
Any spawned sub-agents and their status.
- `label` — task description — status (running/done/failed)
FOCUS-LOG.md with completion date and outcome,...These signals come from indexed source analysis and may lag behind changes. Check the current source files.
# Focus Tracker
Maintain a `FOCUS.md` file in the workspace root as persistent working state.
## When to Read FOCUS.md
- **Every session start** (before responding to first message)
- **After every compaction** (if context feels thin, read it)
- **When the user asks about current work** ("what are we doing?", "where were we?")
## When to Write/Update FOCUS.md
- **When starting a new focused project** — create or replace the active focus
- **When a sub-task completes** — check off items, update status
- **When priorities shift** — user redirects, update immediately
- **When work is DONE** — archive to `FOCUS-LOG.md` and clear FOCUS.md
- **Before compaction memory flushes** — ensure FOCUS.md reflects current state
## FOCUS.md Format
```markdown
# FOCUS — [Project Name]
**Started:** YYYY-MM-DD HH:MM UTC
**Status:** active | paused | blocked
**Context:** One-line summary of WHY we're doing this
## Objective
What we're trying to accomplish (1-3 sentences max)
## Plan
Numbered steps. Check off as completed.
- [x] Step 1 — done
- [ ] Step 2 — in progress (note current state)
- [ ] Step 3 — next
## Active State
What's happening RIGHT NOW. What was the last thing done, what's the next action.
This is the most important section — it's the "resume point" after compaction.
## Blockers
Anything waiting on the user, external systems, or decisions.
## Sub-Agents
Any spawned sub-agents and their status.
- `label` — task description — status (running/done/failed)
```
## Rules
1. **One focus at a time.** If the user pivots, archive the old focus first.
2. **Keep it short.** FOCUS.md should be <50 lines. It's a resume point, not a journal.
3. **Active State is sacred.** Always update it before stopping work. Future-you reads this first.
4. **Don't duplicate memory files.** FOCUS.md tracks *what we're doing now*. Daily memory files track *what happened*. Different jobs.
5. **Archive when done.** Append completed focuses to `FOCUS-LOG.md` with completion date and outcome,...Task Router
Register, communicate, and earn on the x402hub AI agent marketplace. Use when an agent needs to register on x402hub, browse or claim bounties, submit deliverables, send messages to other agents via x402 Relay,...
Real-time event bus for AI agents. Publish, subscribe, and share live signals across a network of agents with Unix-style simplicity.
OpenClaw integration guidance for CAPTCHAS Agent API, including OpenResponses tool schemas and plugin tool registration.