Install
$ agentstack add skill-kumo-ai-kumo-coding-agent-kumo-issue ✓ 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
File a kumo-coding-agent Issue
Create a structured GitHub issue on kumo-ai/kumo-coding-agent for agent gaps, bugs, or feature requests.
This command works in both Claude Code (interactive) and Codex (headless). In Codex, provide a description as the argument — interactive prompting is not available.
User input: $ARGUMENTS
Instructions
Step 1: Validate GitHub CLI Auth
Run:
gh auth status
If gh is not authenticated, tell the user to run gh auth login -h github.com first and stop before gathering more information.
Step 2: Gather Information
If $ARGUMENTS is provided, parse it to understand the issue.
If $ARGUMENTS is empty, ask the user these questions (skip in headless mode):
- What happened? (What were you trying to do?)
- Which skill or context doc was involved? (If known)
- What did you expect vs what happened?
Step 3: Classify the Issue
Determine the type based on the description:
| Type | Signal | Label | |------|--------|-------| | gap | "agent didn't know", "missing info", "couldn't answer" | gap | | bug | "wrong info", "incorrect", "outdated", "says X but should be Y" | bug | | feature | "add support for", "new skill", "new vertical", "would be nice" | enhancement |
Step 4: Identify Affected Files
Search for files related to the issue:
grep -rl "" context/ skills/
If the user mentioned a specific file, verify it exists and note the relevant section.
Also check if this is already tracked:
grep -i "" context/_gaps.yaml
If already tracked, tell the user and ask if they still want to file an issue.
Step 5: Compose the Issue
Title format: kumo:
Examples:
kumo: missing Databricks Unity Catalog connector docskumo: pql-syntax.md lists MODE as valid aggregationkumo: add healthcare/clinical trials vertical
Body template:
## Type
## Affected File(s)
- `` (line ~N)
## Description
## Expected Behavior
## Current Behavior
## Suggested Fix
## Context
---
*Filed via `/kumo-issue` by @REPORTER*
Step 6: Create the Issue
First, capture the reporter's GitHub identity:
gh_user=$(gh api user --jq '.login')
Replace @REPORTER in the body template with @$gh_user.
Run:
gh issue create \
--repo kumo-ai/kumo-coding-agent \
--title "" \
--label "kumo-coding-agent," \
--assignee "manushmurali-kumo" \
--body ""
Use a heredoc for the body to preserve formatting.
If gh is not authenticated, tell the user to run gh auth login -h github.com first and provide the exact command to retry.
Step 7: Follow Up
After the issue is created:
- Print the issue URL
- Tell the user: "Your issue has been filed. A Kumo team member will review it and follow up with you."
- If the type is gap, suggest also adding an entry to
context/_gaps.yaml with status: open
- If the type is bug and the fix is obvious, suggest running
/kumo-pr to fix it directly
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: kumo-ai
- Source: kumo-ai/kumo-coding-agent
- License: MIT
- Homepage: https://kumo.ai
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.