github-bug-report-triage

github-bug-report-triage is a skill for Claude Code, Codex from OutlineDriven/odin-claude-plugin. It costs 43 tokens per session (1,006 once invoked), scanned A, original, Apache-2.0.

Use when evaluating whether a bug issue has sufficient detail and identifying missing reporter information. Not for non-bug issues or backlog triage: use github-backlog-triage.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present.

Part of the odin-git plugin — 46 skills shipped together

Install with agentmods
npx agentmods add skills/outlinedriven/odin-claude-plugin/github-bug-report-triage
Install

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.

Any agent
npx skills add OutlineDriven/odin-claude-plugin --skill github-bug-report-triage
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/odin-claude-plugin

Made for: Claude Code, Codex.

Or install odin-git, the plugin that ships this one along with the rest of its 46 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 github-bug-report-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/github-bug-report-triage.svg)](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/github-bug-report-triage)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/github-bug-report-triage"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/github-bug-report-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,006 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 unknown 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 $0.00043 $0.01006
Opus 5 $0.00022 $0.00503
Sonnet 5 $0.00009 $0.00201
Haiku 4.5 $0.00004 $0.00101

Measured today against content hash 9fb9aac17a30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

github-bug-report-triage 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 today.

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/odin-git/skills/github-bug-report-triage/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub bug report triage

Contract

Field Bound contract
Trigger Evaluating whether a bug issue has sufficient detail and identifying missing information from the reporter.
Authority Remote: drafts one missing-information comment for a GitHub issue and previews it with the target issue; the human posts it or applies any label. Requires explicit human invocation; the model never posts, labels, closes, or otherwise mutates the issue or repository on its own.
Side effect A comment on the GitHub issue requesting missing information, or a confirmation that the issue is actionable. Posting is a remote mutation performed or explicitly authorized by the human; the model never posts autonomously.
Done Ready issues are confirmed actionable; missing-info issues receive specific, constructive feedback listing exactly what is needed.

Inputs

A GitHub bug issue (number or URL) in the target repository. Required.

The project bug-report issue template, if one exists. Optional; located by the procedure.

Procedure

  1. Bound scope to a single bug issue. Do not edit, label, close, or post anything until the human authorizes. Done when: scope is bounded to a single bug issue, and no edit, label, close, or post has been made.
  2. Read the issue title, body, and existing comments. Done when: the issue title, body, and existing comments are read and recorded.
  3. If the issue is a feature request or a question, stop: do not evaluate it as a bug report. Done when: the issue is confirmed to be a bug, or the run stops with a stated classification as feature request or question.
  4. Locate the project bug-report template in this order: .github/ISSUE_TEMPLATE/bug_report.md, .github/ISSUE_TEMPLATE/bug_report.yml, .github/ISSUE_TEMPLATE/*.md, .github/ISSUE_TEMPLATE.md, ISSUE_TEMPLATE.md. If none exists, evaluate the issue against this bug-report field set: Summary (what is broken), Expected behavior, Actual behavior (including any error messages), Steps to reproduce or a reproduction link / minimal code example, and Environment (OS, runtime, version or commit, install method). Done when: the bug-report template is located at one of the searched paths, or its absence is confirmed and the default field set is applied.
  5. Judge actionability against the minimum information needed to investigate, not against every template field being filled: a clear problem description plus a reproduction path (steps, link, or minimal code) or enough context to debug is sufficient. Done when: actionability is judged against the minimum information needed to investigate (problem description plus reproduction path or debug context), and the judgment is recorded with its reasoning.
  6. Classify the issue. Ready: clear problem description, a reproduction path or sufficient debug context, and actually a bug. Needs-info: vague description, missing reproduction and no code example, unclear expected behavior, or missing critical context such as an error message. Done when: the issue is classified as Ready or Needs-info, and the classification names the specific evidence or gap that determined it.
  7. If Ready, confirm the issue is actionable. If Needs-info, list each specific missing item constructively. Done when: a Ready issue is confirmed actionable, or a Needs-info issue has each specific missing item listed constructively.
  8. Draft the comment text. Preview the comment and the target issue to the human. The human posts the comment or applies any label; the model does not post, label, or close autonomously. Done when: the comment text is drafted and previewed to the human with the target issue, and no comment is posted, no label applied, and no issue closed by the model.

Read the full file on GitHub · 44 lines

Files

What ships with it

1 file 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. today First seen · 44 lines · 43 tokens per session scan A 9fb9aac17a30

Subscribe to this mod's changes

github-bug-report-triage is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 1,006 once invoked, about $0.0002 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 2026-09-06.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens