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.
git clone --depth 1 https://github.com/vepo/issuesWrote 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.
[](https://agentmods.dev/rules/vepo/issues/development-process)<a href="https://agentmods.dev/rules/vepo/issues/development-process"><img src="https://agentmods.dev/badge/rules/vepo/issues/development-process/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/vepo/issues/development-process"><img src="https://agentmods.dev/badge/rules/vepo/issues/development-process.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.03938 | $0.03938 |
| Opus 5.5 | $0.01575 | $0.01575 |
| Sonnet 5.5 | $0.00788 | $0.00788 |
| Haiku 4.5 | $0.00394 | $0.00394 |
Grade A, and why
development-process 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development process (mandatory)
No production or test code until phases 1–4 are complete for the current changelog entry. Template: feature/README.md. Feature analysis: change-request-analysis.mdc. Architecture design: architecture-design.mdc.
Strict phase gate
Phases are sequential and mandatory. Never skip phase 2, phase 3, or phase 4.
planned → architecture-ready → tasks-ready → approved → in-progress → done
(feature) (architecture) (task break) (explicit (TDD only)
task approval)
| Action | Phase | Allowed edits |
|---|---|---|
| Feature analysis, feature questions (FQn) | 1 | feature/*.md, docs/**, domain spec |
| Architecture design, architecture questions (AQn) | 2 | feature/*.md, docs/**, domain spec, ARCHITECTURE.md |
| Answer FQn or AQn in chat or feature doc | 1 or 2 (still) | feature/*.md, docs/**, ARCHITECTURE.md only — not src/main/**, src/test/**, src/main/webui/** |
| Task break (Tasks + Test coverage + Feature checklist) | 3 | feature/*.md |
| User approves task IDs | 4 | feature/*.md (record approval) |
| TDD implementation | 5 | src/main/**, src/test/**, src/main/webui/**, docs as needed |
Open question kinds
| Kind | Prefix | Phase | Decides |
|---|---|---|---|
| Feature question | FQn | 1 | Product scope, UX, wireframe, domain rules, user-visible behaviour |
| Architecture question | AQn | 2 | Packages, layers, API shape, schema, cross-context integration, technical trade-offs |
Legacy undifferentiated Qn in existing feature docs are treated as FQn until updated.
Answering open questions ≠ development approval
Forbidden: starting phase 5 because the user answered FQ1, AQ2, chose an option, said "yes"/"big-bang", or clarified scope. Those actions only update the relevant questions table (status answered, Answer column) — they do not authorize coding.
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.
- 1mo ago First seen · 223 lines · 3,938 tokens per session scan A 60f2a5bcfa0f
development-process is a cursor rule published in the GitHub repository vepo/issues (8 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3,938 tokens to every session, about $0.0158 per session on Opus 5.5. 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.
Other cursor rules, from other repositories
always-on
Spec-driven Spring Boot 4 — global guardrails that compensate for Windsurf's lack of a pre-tool-use hook.
production-code
Production code rule — TDD precondition + Spring Boot 4 conventions.
test-code
Test code rule — JUnit 5, Testcontainers, traceability tagging.
mcpnuke-tests
Test conventions for mcpnuke — enforces TDD workflow.
debug-issue
When the user reports a bug, an error, or unexpected behavior. Enforces four structured phases — reproduction, failing test, root cause isolation, fix and verify — to stop guess-and-check loops.
common-testing
Testing requirements: 80% coverage, TDD workflow.