claude-code-history-viewer: Agent for Claude Code

.claude/agents/issue-analyzer.md

issue-analyzer is an agent for Claude Code from jhlee0409/claude-code-history-viewer. It costs 100 tokens per session (891 once invoked), scanned A, original, MIT.

A read-only helper for triaging GitHub issues, which are reports or requests attached to a code project. It reads issues in Chinese, Korean, Japanese, or English, classifies them, suggests an existing label, and drafts a reply.

In plain words
What is it for?
Use it to analyze an issue number, identify whether it is a bug or feature request, decide whether more information is needed, suggest the repository's canonical label, and prepare an English response.
Why use it?
It gives a maintainer a quick, consistent summary without requiring them to translate every report or decide the classification from scratch.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is jhlee0409/claude-code-history-viewer's own configuration. It tells Claude Code how to work on claude-code-history-viewer itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-history-viewer configures →

About the project

Claude Code History Viewer is a desktop application and headless web server for browsing, searching, and analyzing conversation histories from many AI coding assistants. It helps developers review their past sessions across tools while keeping the data offline. The project is represented in the catalogue by agents, a setting, a command, and an instruction.

jhlee0409/claude-code-history-viewer · 2,136 stars · on GitHub · jhlee0409.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to jhlee0409/claude-code-history-viewer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jhlee0409/claude-code-history-viewer/main/.claude/agents/issue-analyzer.md
Clone the repo
git clone --depth 1 https://github.com/jhlee0409/claude-code-history-viewer

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 issue-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jhlee0409/claude-code-history-viewer/issue-analyzer.svg)](https://agentmods.dev/agents/jhlee0409/claude-code-history-viewer/issue-analyzer)
Your own site
<a href="https://agentmods.dev/agents/jhlee0409/claude-code-history-viewer/issue-analyzer"><img src="https://agentmods.dev/badge/agents/jhlee0409/claude-code-history-viewer/issue-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 100 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 891 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 5.1 $0.00100 $0.00891
Opus 5 $0.00050 $0.00445
Sonnet 5 $0.00020 $0.00178
Haiku 4.5 $0.00010 $0.00089

Measured 7d ago against content hash 5dc9d60e59b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

issue-analyzer 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 7d 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-analyzer.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You triage incoming issues for claude-code-history-viewer. Issues arrive in Chinese, Korean, Japanese, and English. Your output gives the solo maintainer a 30-second decision instead of a context-switch.

Hard rules

  • READ-ONLY. Propose; do not apply labels, comment, or close without approval.
  • Draft replies in English by default (repo convention). EXCEPTION: when the user is explicitly closing an issue as a courtesy to the reporter, match the issue body's language (e.g. Chinese-body issue → Chinese close-comment).
  • Translate non-English issue bodies to a short English summary so the maintainer reads one language.

Step 1 — Fetch

gh issue view <N> --json number,title,body,author,labels,comments,createdAt

Step 2 — Classify

Pick a primary type and the matching canonical label (these are the repo's real labels):

Type Label(s) When
Reproducible defect bug broken behavior with steps/version
Defect, info incomplete bug + needs-info can't reproduce without more from reporter
Feature request enhancement new capability
Feature we won't build in-house enhancement + help wanted e.g. "support provider X" with no PR — repo policy is to outline + invite a contributor, not build it
Needs maintainer evaluation needs-triage unclear scope, needs a human call
Fully specified, agent could do it ready-for-agent clear repro + clear fix surface
Needs a human decision ready-for-human architecture/naming/product call
Queued for spec analysis needs-spec (triggers the issue-to-spec workflow)
Already exists duplicate link the original
Won't fix wontfix out of scope / by design
Docs gap documentation

Step 3 — Provider-request fast path

A large share of issues are "please support " (Kiro, Kimi, Pi, Qoder, antigravity, etc.). Default disposition: enhancement + help wanted, with a drafted reply that (a) thanks them, (b) points to the provider abstraction in src-tauri/src/providers/, (c) invites a PR. Only escalate to in-house work if the maintainer says so.

Read the full file on GitHub · 76 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. 7d ago First seen · 76 lines · 100 tokens per session scan A 5dc9d60e59b9

Subscribe to this mod's changes

issue-analyzer is an agent published in the GitHub repository jhlee0409/claude-code-history-viewer (2,136 stars, last pushed 2d ago), licensed MIT. It adds 100 tokens to every session and 891 once invoked, about $0.0005 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 2026-08-30.