Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ruchernchong/claude-kit --skill create-issuegit clone --depth 1 https://github.com/ruchernchong/claude-kitWrote 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/ruchernchong/claude-kit/create-issue)<a href="https://agentmods.dev/skills/ruchernchong/claude-kit/create-issue"><img src="https://agentmods.dev/badge/skills/ruchernchong/claude-kit/create-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/ruchernchong/claude-kit/create-issue"><img src="https://agentmods.dev/badge/skills/ruchernchong/claude-kit/create-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00018 | $0.00635 |
| Opus 5.5 | $0.00007 | $0.00254 |
| Sonnet 5.5 | $0.00004 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
create-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.
What it actually says
Language Conventions
Infer language style from the project:
- Analyze existing issues, documentation, and commit messages to detect the project's language variant (US English, UK English, etc.)
- Match the spelling conventions found in the project (e.g., "initialize" vs "initialise", "behavior" vs "behaviour")
- Maintain consistency with the project's established language style throughout issue titles and descriptions
Create a GitHub issue with the following workflow:
- Check if we're in a GitHub repository and get owner/repo info
- Check for organization issue types:
- Use
github/list_issue_typesMCP tool with the repository owner - If issue types exist, select the most appropriate type based on the issue context (e.g., "Bug", "Feature", "Task")
- Note: This will fail for user-owned repositories (not organizations) - this is expected, proceed without issue type
- Use
- Check for ISSUE_TEMPLATE format:
- Look for issue templates in
.github/ISSUE_TEMPLATE/or.github/directories - If templates exist, use the most appropriate template format (bug report, feature request, etc.)
- Parse template structure and fill in the required sections
- Look for issue templates in
- If no ISSUE_TEMPLATE exists, use custom format:
- Infer issue title from user's request context
- Generate appropriate issue description based on the context
- Get current user for assignment:
- Use
github/get_meMCP tool to get the current authenticated user's login
- Use
- Create issue using
github/issue_writeMCP tool:- Set
method: "create" - Include
owner,repo,title,body - Include
typeparameter if organization issue types are available (from step 2) - Include
assigneesarray with current user's login for self-assignment - If assignment fails (user not a collaborator), the issue will still be created without assignment
- Set
- Optionally add existing labels or milestone (only use labels that already exist in the repository)
- Additional assignees can be added to the
assigneesarray
- Additional assignees can be added to the
For the issue title:
- Use natural, descriptive language (NOT conventional commits format like "feat:", "fix:", "chore:")
- Make it clear and specific to the problem or feature
- Keep it concise but informative
For the issue description (when using custom format):
- Include clear problem statement or feature request
- Add steps to reproduce (if bug report)
- Keep it structured and actionable
For ISSUE_TEMPLATE format:
- Follow the exact template structure and required fields
- Fill in template placeholders with relevant information from user context
- Maintain template formatting and sections
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 · 57 lines · 18 tokens per session scan A 0f674af0a692
create-issue is a skill published in the GitHub repository ruchernchong/claude-kit (0 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 635 once invoked, about $0.0001 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 2026-09-01.
Other skills, from other repositories
github
Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.
full-sdc
EXECUTE lean Full Story Development Cycle for one story: plan via CLI, run validate → develop → review (QG loop) → close with Sequence Lock, durable progress under .aiox/sdc/. Use when: full-sdc, full cycle, SDC, run story end-to-end.
wave-execute
EXECUTE a lean wave — plan story DAG + file-ownership batches via CLI, dispatch full-sdc per story, fan-in check, hand off merge to @devops. Use when: wave-execute, run wave, epic wave, parallel stories SDC.
close-story
Finalize bookkeeping for a story already completed by QA. Never changes lifecycle status. Use when: close story, close-story, story Done, /close-story.
develop-story
Implement a story (Ready → InProgress → ready for review). Runs the OSS develop task. Use when: develop story, develop, /develop-story, implement ACs.
review-story
QA gate for a story — verdict PASS/CONCERNS/FAIL/WAIVED + lifecycle transition. Use when: review story, qa gate, qa-gate, /review-story.