issue-conventions-guide

issue-conventions-guide is a skill for Claude Code from artem-from-ua/claude-plugins. It costs 137 tokens per session (798 once invoked), scanned A, original, MIT.

A routing guide for applying a repository's rules when creating, editing, closing, or labeling GitHub issues. An issue is a tracked task or problem in a project.

In plain words
What is it for?
Use it when managing issue titles, labels, scope, priority, classification, or closing reasons in a GitHub repository.
Why use it?
It prevents an agent from inventing labels or priorities and sends each issue change to the appropriate rules.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the issue-conventions plugin — 4 skills shipped together

Good fit Use it when managing issue titles, labels, scope, priority, classification, or closing reasons in a GitHub repository.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add artem-from-ua/claude-plugins
Claude Code
/plugin install issue-conventions

Made for: Claude Code.

Or install issue-conventions, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

agentmods badge for issue-conventions-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/artem-from-ua/claude-plugins/issue-conventions-guide/github.svg)](https://agentmods.dev/skills/artem-from-ua/claude-plugins/issue-conventions-guide)
Your own site
<a href="https://agentmods.dev/skills/artem-from-ua/claude-plugins/issue-conventions-guide"><img src="https://agentmods.dev/badge/skills/artem-from-ua/claude-plugins/issue-conventions-guide/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.

agentmods 80×15 button for issue-conventions-guide

Your own site · 80×15
<a href="https://agentmods.dev/skills/artem-from-ua/claude-plugins/issue-conventions-guide"><img src="https://agentmods.dev/badge/skills/artem-from-ua/claude-plugins/issue-conventions-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 798 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00137 $0.00798
Opus 5.5 $0.00055 $0.00319
Sonnet 5.5 $0.00027 $0.00160
Haiku 4.5 $0.00014 $0.00080

Measured 1mo ago against content hash afe26c985dd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

issue-conventions-guide 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.

plugins/issue-conventions/skills/issue-conventions-guide/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Conventions — Dispatcher

This skill routes work to a subagent. It carries no taxonomy rules of its own — rules and issue bodies stay in the subagent so they never enter the session context.

Step 1: Resolve the config

Read the first that exists: .claude-plugin/issue-conventions.json → .claude/issue-conventions.json → ~/.claude/issue-conventions.json.

A hit without a taxonomyDocument field counts as no taxonomy.

No config, or the document is missing or unparseable: do NOT invent a taxonomy and do NOT block the operation. Apply whatever labels already exist in the repo, say once per session — "This repo has no issue taxonomy; /issue-conventions-setup can design one" (or name the broken path) — then carry on.

Step 2: Route

Pick the row that matches what is about to happen. Launch the subagent with the instruction file as its system prompt, and pass it the taxonomyDocument path plus the issue data. Use models.<key> and efforts.<key> from the config.

Situation Instructions Model key
A new issue is being created ${SKILL_DIR}/references/classify-new.md classifyNew
An existing issue changes scope, priority, severity, or classification; or is closed with a reason ${SKILL_DIR}/references/reclassify.md reclassify
Several issues at once (splitting an epic, a small cleanup) ${CLAUDE_PLUGIN_ROOT}/templates/batch-classify.md batchClassify
The whole backlog stop — tell the user to run /issue-conventions-relabel —
"Is everything still consistent?" stop — tell the user to run /issue-conventions-drift —

The subagent cannot see this conversation. Pass it a 2–3 sentence summary of what the issue is about, alongside the issue number or the draft title and body.

Step 3: Act on what comes back

Every classification subagent returns the same shape:

{ "labels": ["type:x", "priority:y"], "title": "...", "confidence": "high|low",
  "question": null }
  • question is null — apply it. Labels go in one call: gh issue create --label "a,b,c". For an edit use --add-label / --remove-label, never --label (it overwrites).
  • question is set — it holds text and options. Raise it with AskUserQuestion in this session (the subagent has no such tool), then apply the answer. If the answer reads like a general rule rather than a one-off, offer to add it to the document's disambiguation section.

Read the full file on GitHub · 53 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 1mo ago First seen · 53 lines · 137 tokens per session scan A afe26c985dd4

Subscribe to this mod's changes

issue-conventions-guide is a skill published in the GitHub repository artem-from-ua/claude-plugins (11 stars, last pushed 1mo ago), licensed MIT. It adds 137 tokens to every session and 798 once invoked, about $0.0005 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 2026-09-08.