Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vybestack/llxprt-codenpx agentmods add skills/vybestack/llxprt-code/llxprt-issue-workflowWrote 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/vybestack/llxprt-code/llxprt-issue-workflow)<a href="https://agentmods.dev/skills/vybestack/llxprt-code/llxprt-issue-workflow"><img src="https://agentmods.dev/badge/skills/vybestack/llxprt-code/llxprt-issue-workflow/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/vybestack/llxprt-code/llxprt-issue-workflow"><img src="https://agentmods.dev/badge/skills/vybestack/llxprt-code/llxprt-issue-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 15 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 90 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00088 | $0.02078 |
| Opus 5.5 | $0.00035 | $0.00831 |
| Sonnet 5.5 | $0.00018 | $0.00416 |
| Haiku 4.5 | $0.00009 | $0.00208 |
Grade A, and why
llxprt-issue-workflow 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLxprt Issue Workflow
End-to-end workflow for taking a GitHub issue in this repository from intake to a green, review-clean pull request.
1. Setup
- Checkout main and pull latest from origin. Do NOT delete any files or run
git clean— justgit checkout main && git pull. - Create branch
issueNUM(e.g.issue1234). - Use
ghto pull the issue and its comments, AND assign the issue to acoliver:gh issue edit NUM --add-assignee acoliver. - Always use
ghfor issues/PRs/comments — never webfetch. Use proper gh command syntax and avoid unescaped backticks in bodies/comments (they trigger shell command substitution).
2. Research and plan
- Research the issue in the codebase using the description and comments as the starting point.
- Create a test-first plan following dev-docs/RULES.md behavioral tests (no mock
theater). See the
typescript-test-writingskill for the distilled test rules. - Plan documents go in
project-plans/, NEVER indev-docs/. dev-docs/ holds durable engineering reference material (PLAN.md, RULES.md, architecture notes); project-plans/ holds per-issue and per-feature planning. Writing a plan to dev-docs/plans/ is wrong — dev-docs/PLAN.md and dev-docs/PLAN-TEMPLATE.md are the methodology you follow, not the destination you write to. This is enforced by scripts/check-doc-placement.ts, which fails if dev-docs/plans/ exists. - Temporary issue state belongs under project-plans/, not dev-docs/.
Scope rules
- Scope is based on functionality, not line counts. Never add line or file counts for issue scope; if an issue contains them, ignore them.
- Do not update unrelated project-plan files owned by other issue efforts except when required to resolve conflicts or unblock the current PR. CI, lint, test, and formatting failures automatically authorize bounded scope expansion needed to make the PR green; do not ask for approval based only on file or line counts. Ask only before major functional or architectural expansions beyond the issue scope.
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 Changed · +1 tokens per session 30f4e50afc00
- 1mo ago First seen · 168 lines · 87 tokens per session scan A a96239f52c40
llxprt-issue-workflow is a skill published in the GitHub repository vybestack/llxprt-code (702 stars, last pushed today), licensed Apache-2.0. It adds 88 tokens to every session and 2,078 once invoked, about $0.0004 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
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.
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…
cuga-github-issues
Create GitHub issues for cuga-agent (bugs, features, epics, designs, and related work) against origin using gh, with epic → feature → issue hierarchy and GraphQL sub-issue linking. Use when the user says create new issues, report a bug, file a bug, feature request, new feature, create an epic, GitHub issue, sub-issue…
implement-issue
Implement a Linear brief in a named GitHub repo. Use when the brief skill is implement-issue or the user wants a new branch and draft PR.