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.
git clone --depth 1 https://github.com/vchelaru/XnaFiddleWrote 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/rules/vchelaru/xnafiddle/issue-workflow)<a href="https://agentmods.dev/rules/vchelaru/xnafiddle/issue-workflow"><img src="https://agentmods.dev/badge/rules/vchelaru/xnafiddle/issue-workflow.svg" alt="Measured on agentmods" 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 | $0.00399 | $0.00399 |
| Opus 5 | $0.00199 | $0.00199 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
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 2d 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
Issue workflow & manual testing
Full detail: .claude/skills/issue-workflow/SKILL.md. On GitHub issue work (#N or issue URL), load that skill first.
Issue flow (summary)
- Read issue and comments (
gh issue view <n> --comments). - Branch off
main(feat/…/fix/…) — never commit issue work onmain. - Build:
dotnet build XnaFiddle.BlazorGL/XnaFiddle.BlazorGL.csproj - Manual testing (below) when the change affects the running app.
- Open PR immediately (
Closes #<n>); don't wait for manual sign-off.
Manual testing — do not skip or bury in the PR
If the change needs hand testing (most UI/behavior work — compile banner, export dialog, editor tabs, game run, etc.):
- Tell the user explicitly they should test it — don't only list steps in the PR body.
- Open the solution first (before or while writing steps), so VS loads in parallel:
Startup project: XnaFiddle.BlazorGL → F5.Start-Process "XnaFiddle.sln" - Then give concise numbered steps: what to run/click, expected behavior, and what failure looked like before.
Skip manual-test handoff only when the change is genuinely untestable by hand (pure refactor, version bump with no UI surface, etc.) — say so briefly.
Common mistake
Opening the PR with a test-plan checkbox is not a substitute for telling the user to test and opening XnaFiddle.sln for them.
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.
- 2d ago First seen · 35 lines · 399 tokens per session scan A 9ac12b9302ea
issue-workflow is a cursor rule published in the GitHub repository vchelaru/XnaFiddle (13 stars, last pushed 2d ago), licensed MIT. It adds 399 tokens to every session, about $0.0020 per session on Opus 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 2026-09-04.
Other cursor rules, from other repositories
workflow
Development workflow and commit practices.
commit-checks
Run gofmt, go vet, and unit tests before committing Go files.
hook-commits
Set up pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
cmd-build
Implement the next task incrementally — build, test, verify, commit.
quality-gates
Enforce quality checks before commits - lint, typecheck, and test affected code.
pre-commit-lint-format
Enforce Prettier format, ESLint lint, and unit tests before every commit in lfx-self-serve.