analyze-issue

A GitHub issue analysis workflow that turns an issue into a detailed plan for changing a codebase. GitHub issues are records of bugs, feature requests, and other work.

In plain words
What is it for?
Use it to prepare an implementation specification, including a technical approach, step-by-step tasks, test cases, reusable utilities, and files to modify or create. TDD means writing a failing test before the code that makes it pass.
Why use it?
It connects the issue's requirements with the affected code, tests, files, success criteria, and limits of the work.

Cursor rule

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 rules/steipete/agent-rules/analyze-issue
Clone the repo
git clone --depth 1 https://github.com/steipete/agent-rules
Per session 246 This file is loaded in full into every session.
When invoked 246 The same file — it is already loaded in full.
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 $0.00246 $0.00246
Opus 5 $0.00123 $0.00123
Sonnet 5 $0.00049 $0.00049
Haiku 4.5 $0.00025 $0.00025

Measured 2d ago against content hash dd5eb7f0e68e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-issue 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

project-rules/analyze-issue.mdc · 44 lines

What it actually says

Analyze Issue

Fetch GitHub issue details and create a comprehensive implementation specification.

Template Sections:

1. Issue Summary

Brief overview of the issue

2. Problem Statement

Clear definition of what needs to be solved

3. Technical Approach

High-level solution approach and architecture decisions

4. Implementation Plan

Step-by-step breakdown of implementation tasks

5. Test Plan

Testing strategy and test cases to write

6. Files to Modify

List of existing files that need changes

7. Files to Create

New files that need to be created

8. Existing Utilities to Leverage

Project utilities/helpers that can be reused

9. Success Criteria

Measurable criteria for completion

10. Out of Scope

What won't be addressed in this implementation

Process:

  1. Fetch issue details using gh issue view <issue_number>
  2. Review related code and project structure
  3. Analyze requirements thoroughly
  4. Create detailed technical specification
  5. Follow strict TDD principles, KISS approach
  6. Enforce 300-line file limit where applicable
  7. Output the full technical specification for review
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. 2d ago First seen · 44 lines · 246 tokens per session scan A dd5eb7f0e68e

Subscribe to this mod's changes

analyze-issue is a cursor rule published in the GitHub repository steipete/agent-rules (5,696 stars, last pushed 4mo ago), licensed MIT. It adds 246 tokens to every session, about $0.0012 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.