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 nimble-giant/nimble-mold --skill start-issuegit clone --depth 1 https://github.com/nimble-giant/nimble-moldWrote 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/nimble-giant/nimble-mold/start-issue)<a href="https://agentmods.dev/skills/nimble-giant/nimble-mold/start-issue"><img src="https://agentmods.dev/badge/skills/nimble-giant/nimble-mold/start-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/nimble-giant/nimble-mold/start-issue"><img src="https://agentmods.dev/badge/skills/nimble-giant/nimble-mold/start-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 | $0.00034 | $0.00696 |
| Opus 5.5 | $0.00014 | $0.00278 |
| Sonnet 5.5 | $0.00007 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
start-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 2mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start Issue
Fetch a {{scm.provider}} issue and begin implementation.
Usage
/start-issue <issue-number>
/start-issue <issue-url>
/start-issue --local <filename>
/start-issue --local
Flags
--local [filename]: Read from a local markdown file in theplans/directory instead of fetching a {{scm.provider}} issue. Iffilenameis omitted, list available plans and prompt the user to choose one.
Examples
/start-issue 1234- Start work on issue #1234/start-issue {{scm.base_url}}/your-org/your-repo/issues/1234- Start work using full URL/start-issue --local feat-web-add-control-family-status-card- Start work from a local plan file/start-issue --local- List available local plans and choose one
Workflow
When this command is used:
GitHub Mode (default)
-
Fetch the issue details using
{{issue.view}} -
Create a todo list with tasks derived from the issue requirements
-
Begin implementation following the issue requirements and acceptance criteria
-
Use issue context to inform commit messages and implementation approach
Local Mode (--local flag)
- Resolve the plan file:
- If a filename was provided, look for
plans/<filename>.md(.mdextension may be omitted) - If no filename was provided, list all
*.mdfiles in theplans/directory and ask the user to choose one
- If a filename was provided, look for
- Read the local plan file and use it as the issue specification
- Create a todo list with tasks derived from the plan requirements
- Begin implementation following the plan's requirements and acceptance criteria
- Use the plan filename to inform commit messages in place of an issue number
Scope Boundaries
IMPORTANT: Stay focused on the specified issue ONLY.
- Do NOT search for, fetch, or work on related issues, sub-issues, parent issues, or adjacent issues
- Do NOT follow
#XXXXreferences in the issue body to other issues - Do NOT use
{{issue.list}}or{{issue.search}}to discover other issues - If the issue description mentions other issues for context, note them but do NOT expand scope to include their requirements
- All work should be scoped strictly to what the specified issue describes
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.
- 2mo ago First seen · 78 lines · 34 tokens per session scan A 5d4e34517b17
start-issue is a skill published in the GitHub repository nimble-giant/nimble-mold (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 696 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 2026-08-31.
Other skills, from other repositories
antfu-issue-triage
Triage open issues and PRs of the current GitHub repo - find already-fixed, duplicate, and spam items, suggest labels, gauge demand from reactions and comments, then present a table of proposed actions and comments for confirmation before touching anything. Use when asked to triage, organize, clean up, or groom issues…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
llxprt-issue-workflow
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the zai-glm-flash smoke test), open code review (ocr)…
connect
Choose which wiki this session uses, the team project's pages on the Nimbalyst server or the project's local wiki of files, and connect a repository to its team project. Use at the start of a task before any wiki tool, when a wiki tool returns reponotbound, ambiguousproject, pinmismatch, projectnotaccessible…