Borrowing it
Nothing to install: this file belongs to kumo-ai/kumo-coding-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kumo-ai/kumo-coding-agent/main/.claude/skills/kumo-issue/SKILL.mdgit clone --depth 1 https://github.com/kumo-ai/kumo-coding-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kumo-ai/kumo-coding-agent/kumo-issue)<a href="https://agentmods.dev/skills/kumo-ai/kumo-coding-agent/kumo-issue"><img src="https://agentmods.dev/badge/skills/kumo-ai/kumo-coding-agent/kumo-issue/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kumo-ai/kumo-coding-agent/kumo-issue"><img src="https://agentmods.dev/badge/skills/kumo-ai/kumo-coding-agent/kumo-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.00983 |
| Opus 5.5 | $0.00030 | $0.00393 |
| Sonnet 5.5 | $0.00015 | $0.00197 |
| Haiku 4.5 | $0.00008 | $0.00098 |
Grade A, and why
kumo-issue scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 "<relevant keyword>" 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 "<keyword>" 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: <concise description>
Examples:
kumo: missing Databricks Unity Catalog connector docskumo: pql-syntax.md lists MODE as valid aggregationkumo: add healthcare/clinical trials vertical
Body template:
## Type
<gap | bug | feature>
## Affected File(s)
- `<path>` (line ~N)
## Description
<Clear description of the issue>
## Expected Behavior
<What should happen / what info should be there>
## Current Behavior
<What actually happens / what the doc currently says>
## Suggested Fix
<If obvious — otherwise "Needs investigation">
## Context
<Any additional context: SDK version, customer use case, etc.>
---
*Filed via `/kumo-issue` by @REPORTER*
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 143 lines · 76 tokens per session scan A 8c97c040e2e9
kumo-issue is a skill published in the GitHub repository kumo-ai/kumo-coding-agent (39 stars, last pushed 3mo ago), licensed MIT. It adds 76 tokens to every session and 983 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agentbro-pr-merge
Use when reviewing, fixing CI for, approving workflows for, or merging AgentBro pull requests into dev/main, especially external contributor PRs where contributor attribution matters.
release-verification
A release-verification checklist for software versions and packages. It covers changelogs, tests, packaging, installation smoke checks, version-control actions, publishing, and checks after release.
audit-release
A pre-release review assistant that checks whether a software package or plugin is ready to publish.
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.