Install
$ agentstack add skill-xcaeser-work-skill-work-status ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Work / 10. Status
Show only state visible in the current task. Do not steer, interrupt, spawn, create or update goals, change plans, edit files, or run validation. This snapshot need not wait for agents, but a non-blocking status read is never a reason to stop them.
When summarizing quality or compatibility, preserve reliability, user state, truthful evidence, and clean breaks over obsolete paths. If parallel work exists, reconcile each route by approach family, evidence, blocker, and next move rather than reporting activity alone.
- Call
get_goalwhen available. - Call
list_agentswhen available. - Reconcile tool results with launch tables and handoffs already visible in the thread.
- Reconcile any visible Work checklist without changing item states or mode.
- Use established call signs; do not invent one from a task ID.
- Distinguish unavailable, none, not yet verified, and failed.
- Do not infer progress from elapsed time, activity, or a prior status message;
report only the latest concrete evidence visible to this task.
Return:
## Work / 10. Status
**Goal:**
**State:**
**Checklist:** / complete or otherwise dispositioned; blocked, or "None">
| Agent | State | Assignment / approach | Last evidence or blocker |
|---|---|---|---|
| | | | |
**Current step:**
**Blocking decision or evidence gap:**
**Next parent action:**
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: xcaeser
- Source: xcaeser/work-skill
- License: MIT
- Homepage: https://skills.sh/xcaeser/work-skill
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.