Skip to content
Agentmart
Submit a tool

warp-status

Write and report the Warp status file: done, working, and left.

Skill by smlsr

IndexedMIT
Write a review

Chalk Labs

Need help deploying warp-status?

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.

Book a call

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/smlsr-warp-status

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.

We use your email only for this newsletter. Privacy

About

Write and report the Warp status file: done, working, and left. Use when the user asks what is done, what is left, or what is in flight.

Use cases: documents, writing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 2, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/warp-status

What's inside

Skill name
warp-status
Description
Write and report the Warp status file: done, working, and left. Use when the user asks what is done, what is left, or what is in flight.
License
MIT
Instructions
26 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • files: referenced but missing: scripts/resume_hint.py

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Warp status

```bash
python3 <plugin>/scripts/scan.py status --beam .warp/beam.json
python3 <plugin>/scripts/beam.py board --beam .warp/beam.json
```

`scan.py status` prints the resume hint first (`scripts/resume_hint.py`). Follow it. Its last block, the version lines, includes `instance: warp:<instance> host=<host> machine=<machine id>`. Report that line. The instance is six characters that name this Warp run. Its agents carry it in their names (`[warp:<instance>] <ticket> <step>`), every Slack and Teams header ends with it, and `.warp/STATUS.md` and `.warp/status.json` record it. It is how this run is told from another Warp run in the same repo or another one. Do not dispatch from this command. Plugin hooks do not run on cloud runners.

`scan.py ?` and `beam.py ?` print the options. Quote `?` if the shell expands it.

Hand the user these paths:

- `.warp/STATUS.md` — done, working now, left
- `.warp/status.json` — the same, machine-readable, full lists
- `.warp/BOARD.md` — gates, alarms, next ready, tokens, ETA
- `.warp/board.html` — the same board in a browser
- `.warp/warp-complete.html` — the completion report, when the status footer names it

Lead the reply with alarms and stalls, then `in progress N/maxInProgress`, or `holding new launches (N/maxInProgress), N fix workers running` when that cap is full, then `live shuttles N/cap` with the fix workers that are running and the dead tickets waiting for a replacement, then the count of each state, then every ticket that is not merged. For each ticket include the state, the current step, how long it has been in that state, when it was last active, the pull request link, whether Bugbot, CI, and the acceptance criteria passed, the stall flag, the retry count, any alarm, and the next action Warp will take. The same rows are on the beam as `openWork`. Then report the last repair sweep: `sweep: at=...` with findings, actions, skipped, and escalated, or `sweep: none`. Do not paste the whole left list if it is long; point at the file.

The status script prints the plugin version (`Warp v<version>`, the installed copy, and the source copy). If it says the project copy is older, tell the user to run `/warp-uninstall` then `/warp-init`. Do not uninstall unless they ask.

Reconcile live PR and Jira state first if the user asked for current status rather than the last checkpoint.

From smlsr/Warp, MIT.

More from smlsr/Warp

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 8, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from smlsr

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 warp-status 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying warp-status?

CallGet help
Cite this page

warp-status skill. Agent Mart. https://agentmart.dev/skills/smlsr-warp-status (last updated 2026-10-24)