issues CLAUDE.md

Repository instructions for the vepo/issues project, including a required five-phase process for planning and implementing non-trivial changes. TDD means writing tests to describe expected behaviour before implementation.

In plain words
What is it for?
Use them when changing source code, tests, web pages, APIs, data structures, or cross-feature behaviour in that repository.
Why use it?
They prevent premature edits by requiring documented analysis, architecture decisions, task approval, and a controlled implementation process.

Instructions file

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 instructions/vepo/issues/claude-md
Clone the repo
git clone --depth 1 https://github.com/vepo/issues
Per session 1,833 This file is loaded in full into every session.
When invoked 1,833 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 $0.01833 $0.01833
Opus 5 $0.00916 $0.00916
Sonnet 5 $0.00367 $0.00367
Haiku 4.5 $0.00183 $0.00183

Measured 2d ago against content hash d3056fee92c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issues CLAUDE.md 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.

CLAUDE.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

@AGENTS.md

Mandatory development process — read before touching src/

This repo enforces a strict five-phase gate on every non-trivial change (new behaviour, API, UI route, schema, multi-package refactor, or cross-feature bug fix). Full detail: .cursor/rules/development-process.mdc.

1. Feature analysis → 2. Architecture design → 3. Task break → 4. Explicit task approval → 5. TDD implementation
  • No edits to src/main/**, src/test/**, or src/main/webui/** before phase 4. Phases 1–3 only touch feature/<slug>.md, docs/**, and ARCHITECTURE.md.
  • Track open decisions as FQn (feature questions, phase 1) and AQn (architecture questions, phase 2) in the feature doc. Answering a question is not approval — after every FQ/AQ answer, run an impact review (update Impact, Wireframe, Architecture, Feature checklist, tasks) and stop.
  • Phase 4 requires explicit task-ID approval ("Approve T1–T3", "Go ahead with T1"). "Implement it" / "yes" / "do the analysis" do not count — present the task table and ask which IDs to approve instead.
  • Phase 5 is TDD only, per approved task: Red (failing test, no src/main change) → Green (minimal code) → Refactor. Optionally delegate to .cursor/agents/tdd-red.md / tdd-green.md / tdd-refactor.md.
  • Skip the gate only for: typo, comment-only, formatter-only, or docs-only edits.
  • Never end a session with broken code. Before stopping (task done or still in-progress), the tree must compile and touched tests must pass — fix forward or revert, don't leave red.
  • Not in production yet — no legacy/back-compat concerns. Schema changes amend V1.0.0__Database_Creation.sql directly (see .cursor/rules/issues-flyway.mdc); never add new V1.0.x migration files.

Commands

# Backend
mvn quarkus:dev                          # run app (backend :8080 + Angular dev server via Quinoa on :4200)
mvn test                                 # all backend tests
mvn test -Dtest=TicketEndpointTest#methodName   # single test
mvn test -Dtest=ArchitectureTest         # ArchUnit rules
mvn formatter:format                     # Java formatting
mvn verify                               # full backend gate — required before marking a task done

# After backend endpoint changes, regenerate the Angular API client
mvn test && cd src/main/webui && npm run generate:api

# Frontend (src/main/webui)
npm run build                            # production build; runs generate:api via prebuild — use this, not bare `ng build`
npm test -- --no-watch --browsers=ChromeHeadless   # headless test run
npm run lint

Read the full file on GitHub · 80 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. 2d ago First seen · 80 lines · 1,833 tokens per session scan A d3056fee92c2

Subscribe to this mod's changes

issues CLAUDE.md is an instructions file published in the GitHub repository vepo/issues (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,833 tokens to every session, about $0.0092 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.

Related

Other instructions, from other repositories

spartan CLAUDE.md

Instructions for spartan-ng/spartan, covering working in this repo (notes for claude / ai agents), before pushing: run the ci checks locally and pull requests.

spartan-ng/spartan · 438 tokens

fundamental-ngx AGENTS.md

Instructions for SAP/fundamental-ngx, covering angular 22+ development guidelines, persona, quick reference, essential commands and build/lint/test specific library.

SAP/fundamental-ngx · 3,066 tokens

primitives CLAUDE.md

Instructions for radix-ng/primitives, covering radix ng primitives — claude guide, project knowledge, project overview, monorepo structure and naming conventions.

radix-ng/primitives · 9,681 tokens

openbridge-webcomponents watch-radial-instruments.instructions.md

Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering watch & radial instruments, architecture overview, key principle: logic in watch.ts, instruments stay thin, shared sibling modules and layering & stacking pattern.

Ocean-Industries-Concept-Lab/openbridge-webcomponents · 10,138 tokens

openbridge-webcomponents line-area-charts.instructions.md

Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering line/area charts & gauge trend, architecture overview, key principle: logic in base class, subclasses stay thin, base class architecture and line graph (non-filled).

Ocean-Industries-Concept-Lab/openbridge-webcomponents · 4,714 tokens

openbridge-webcomponents setpoint.instructions.md

Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering setpoint system, architecture overview, when to use mixin vs bundle, setpointmixin usage and setpointbundle usage.

Ocean-Industries-Concept-Lab/openbridge-webcomponents · 4,338 tokens