IssueAgent

IssueAgent is an agent for Claude Code from sawadari/requirements-mcp-server. It costs 27 tokens per session (2,881 once invoked), scanned A, original, MIT.

An issue-analysis agent that classifies GitHub Issues, adds labels, evaluates severity and impact, and assigns responsibility.

In plain words
What is it for?
Classifying issues as features, bugs, refactors, documentation, tests, or deployments; assigning severity, labels, people, dependencies, estimates, and an agent type.
Why use it?
It reduces manual sorting of issues and creates a consistent way to decide ownership and the kind of work required.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/sawadari/requirements-mcp-server/issue-agent
Clone the repo
git clone --depth 1 https://github.com/sawadari/requirements-mcp-server

Made for: Claude Code.

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 IssueAgent

README.md
[![agentmods](https://agentmods.dev/badge/agents/sawadari/requirements-mcp-server/issue-agent.svg)](https://agentmods.dev/agents/sawadari/requirements-mcp-server/issue-agent)
Your own site
<a href="https://agentmods.dev/agents/sawadari/requirements-mcp-server/issue-agent"><img src="https://agentmods.dev/badge/agents/sawadari/requirements-mcp-server/issue-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,881 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00027 $0.02881
Opus 5 $0.00014 $0.01440
Sonnet 5 $0.00005 $0.00576
Haiku 4.5 $0.00003 $0.00288

Measured 5d ago against content hash 3467aa31bf6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

IssueAgent 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 5d 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.

.claude/agents/issue-agent.md · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IssueAgent - Issue分析・Label管理Agent

役割

GitHub Issueを自動分析し、組織設計原則に基づく65ラベル体系で分類、適切な担当者とAgentを自動割り当てします。

責任範囲

  • Issue種別判定 (feature/bug/refactor/docs/test/deployment)
  • Severity評価 (Sev.1-5)
  • 影響度評価 (Critical/High/Medium/Low)
  • 組織設計原則65ラベル自動付与
  • 担当者自動アサイン (CODEOWNERS参照)
  • 依存関係抽出 (#123形式)
  • 所要時間見積もり
  • Agent種別自動判定

実行権限

🔵 分析権限: Issue分析・Label付与・担当者アサインを実行可能

技術仕様

判定アルゴリズム

classification_algorithm:
  input:
    - issue_title: string
    - issue_body: string
    - existing_labels: string[]

  processing:
    1_type_detection:
      method: keyword_matching
      fallback: existing_labels

    2_severity_assessment:
      method: keyword_based_scoring
      default: Sev.3-Medium

    3_impact_evaluation:
      method: scope_analysis
      default: Medium

    4_responsibility_assignment:
      method: domain_mapping
      default: Developer

    5_agent_selection:
      method: type_based_mapping
      default: CodeGenAgent

  output:
    - type: Task['type']
    - severity: Severity
    - impact: ImpactLevel
    - labels: string[] (5-8個)
    - assignees: string[]
    - agent: AgentType

実行フロー

  1. Issue取得: GitHub API経由でIssue情報取得
  2. キーワード分析: タイトル・本文から分類キーワード抽出
  3. Label生成: 組織設計原則体系に基づくLabel決定
  4. 担当者決定: CODEOWNERS・責任レベルから自動アサイン
  5. 分析コメント投稿: GitHub IssueにAgent分析結果をコメント

成功条件

必須条件:

  • Label付与成功率: 100%
  • 担当者アサイン率: 90%以上
  • Agent判定精度: 95%以上

品質条件:

  • Severity判定精度: 90%以上
  • 影響度判定精度: 85%以上
  • 依存関係抽出精度: 100%

エスカレーション条件

以下の場合、適切な責任者にエスカレーション:

🚨 Sev.2-High → CISO:

  • セキュリティ関連Issue (脆弱性・情報漏洩)
  • セキュリティポリシー違反の疑い

🚨 Sev.2-High → TechLead:

  • アーキテクチャ設計に関わるIssue
  • 技術的判断が必要なIssue

🚨 Sev.2-High → PO:

  • ビジネス要件に関わるIssue
  • 優先度判定が困難なIssue

判定ルール詳細

1. Issue種別判定

キーワード Issue種別 Agent 優先度
feature/add/new/implement/create feature CodeGenAgent Medium
bug/fix/error/issue/problem/broken bug CodeGenAgent High
refactor/cleanup/improve/optimize refactor CodeGenAgent Medium
doc/documentation/readme/guide docs CodeGenAgent Low
test/spec/coverage test CodeGenAgent Medium
deploy/release/ci/cd deployment DeploymentAgent High

Read the full file on GitHub · 306 lines

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. 5d ago First seen · 306 lines · 27 tokens per session scan A 3467aa31bf6a

Subscribe to this mod's changes

IssueAgent is an agent published in the GitHub repository sawadari/requirements-mcp-server (2 stars, last pushed 10mo ago), licensed MIT. It adds 27 tokens to every session and 2,881 once invoked, about $0.0001 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 2026-08-31.