Borrowing it
Nothing to install: this file belongs to vchelaru/XnaFiddle. 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/vchelaru/XnaFiddle/main/.claude/skills/issue-workflow/SKILL.mdgit 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/skills/vchelaru/xnafiddle/issue-workflow)<a href="https://agentmods.dev/skills/vchelaru/xnafiddle/issue-workflow"><img src="https://agentmods.dev/badge/skills/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 | $0.00058 | $0.01810 |
| Opus 5 | $0.00029 | $0.00905 |
| Sonnet 5 | $0.00012 | $0.00362 |
| Haiku 4.5 | $0.00006 | $0.00181 |
Grade C, and why
issue-workflow scanned grade C with 1 finding 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 yesterday.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
find Submodules/KniSB -type d \( -name obj -o -name bin \) -prune -exec rm -rf {} + How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Workflow
The flow when the user points at a GitHub issue (URL or #N) and asks to fix or implement it.
This grows organically — add a step or a gotcha when one actually bites; keep it lean.
1. Read the issue AND its comments first
Run BOTH gh issue view <n> (title + body) and gh issue view <n> --comments. Plain view
omits the discussion thread, and comments routinely narrow scope, add files to touch, or settle
open questions raised in the body. Read both before touching code.
2. Load matching skills, then invoke the agent
- Load every skill whose trigger matches the area the issue touches (see
CLAUDE.md→ Skills). If none fit, say so briefly and continue — don't silently skip the check. - Announce and invoke the matching agent from
.claude/agents/("Invoking coder agent…") and re-read its file at the start of the task; long sessions drift (seeCLAUDE.md→ Agent Workflow).
3. Branch — never commit issue work to main
Create a branch off main first (feat/…, fix/…).
4. Build to verify
dotnet build XnaFiddle.BlazorGL/XnaFiddle.BlazorGL.csproj
Stale-submodule gotcha: the build can fail with dozens of
CS0579: Duplicate '…AssemblyInfo' attribute errors, all pathed under Submodules/KniSB/**.
These are leftover obj/bin from earlier multi-TFM builds (net45 / netstandard2.0) being
globbed into the net10.0 build — not your change. Clear them and rebuild:
find Submodules/KniSB -type d \( -name obj -o -name bin \) -prune -exec rm -rf {} +
This removes only generated artifacts; the submodule pointer and tracked source are untouched
(it also cleans the dirty M Submodules/KniSB working-tree state those artifacts cause).
5. Set up manual testing — prioritize testing and speed
If the change needs manual testing in the running app (most UI/behavior changes do), get the user testing as fast as possible:
- Open the solution first, before writing anything:
Start-Process "XnaFiddle.sln"(PowerShell). Launch it up front so Visual Studio loads in the background while you write the steps — don't make the user wait on your prose before the IDE is even opening. Exception — mobile testing: if the fix must be verified on a phone (touch UI, mobile layout, anything Android/iOS-specific), do not open the.sln, and do not suggest USB /chrome://inspectdebugging — that route was whack-a-mole and the user abandoned it. Instead have them serve over the LAN and hit it from the phone:dotnet run --project XnaFiddle.BlazorGL --urls "http://0.0.0.0:60441", then openhttp://<machine-LAN-ip>:60441on the phone (same Wi-Fi). Use plain HTTP (avoids the dev-cert-trust problem); it's fine unless the specific test needs a secure context (clipboard / CacheStorage). Find the LAN IP withGet-NetIPAddress -AddressFamily IPv4(the Wi-Fi one, not the172.xWSL vEthernet). The user has a permanent Windows Firewall rule for inbound 60441, so the phone connects without any setup — do not mention firewall, connection troubleshooting, or Incognito in the handoff; that's all handled on their end. Just give them the URL and the marker color (below). - Then write concise, numbered manual steps — what to run, what to click, and what correct behavior looks like (and the failure mode the fix addresses, so the user knows what they're confirming).
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.
- yesterday First seen · 114 lines · 58 tokens per session scan C 1428cc83c923
issue-workflow is a skill published in the GitHub repository vchelaru/XnaFiddle (13 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,810 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
将 Comet GitHub 维护请求路由到基于证据的 PR 审阅、Issue 分诊、本地想法收集、CI 诊断或 Issue 实施流程。用户提到 Comet GitHub Issue/PR 但未指定流程，或询问下一步如何处理时使用。.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".