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.
npx agentmods add rules/vepo/issues/issues-qualitygit clone --depth 1 https://github.com/vepo/issuesWhat 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 | $0.00613 | $0.00613 |
| Opus 5 | $0.00307 | $0.00307 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
issues-quality 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding quality and standards
Working code invariant
Development never ends with non-working code. Before stopping — whether the changelog is done or still in-progress:
- The project compiles (
mvn verifyfor backend;npm run buildwhen webui changed). - Affected tests pass; no new failures in touched code.
- No compile errors or new linter errors in edited files.
If a change breaks the build, fix it or revert it before ending. Partial features stay in-progress; they do not ship broken.
Finish gate (before marking done)
- Mid-task: tiered tests per issues-testing.mdc.
- Backend scope: affected
*Testclasses pass. - Full suite:
mvn verify— same as.github/workflows/build.ymlbackend portion. - Frontend scope:
npm run buildthennpm testinsrc/main/webuiwhen Angular files changed. - IDE:
ReadLintson edited paths — fix new warnings.
Skip gates for docs-only, .mdc-only, or comment-only edits.
What to fix
- Compile errors and test failures from
verify. - New linter issues in touched files.
- Smells you introduced: dead code, swallowed exceptions,
System.out— see issues-java.mdc.
Pre-existing issues elsewhere: fix only if trivial; no scope creep.
Do not finish while
mvn verifyfails on backend changes you made.npm run buildfails on frontend changes you made.- New linter problems in files you changed.
- Failing tests remain in touched code.
- Any compile error or broken test exists in your diff — including when stopping mid-task (
in-progressis allowed; broken code is not).
Standards (file-scoped detail)
| Topic | Rule |
|---|---|
Java style, logging, var, streams |
issues-java.mdc |
| Imports and formatting | issues-format-imports.mdc |
| String building | issues-strings.mdc |
| HTTP Request/Response records | issues-http-contract.mdc |
| Layered architecture | issues-layered-architecture.mdc |
| JPA / repositories | issues-jpa.mdc |
| Angular conventions | issues-angular.mdc |
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.
- 2d ago First seen · 59 lines · 613 tokens per session scan A 71013033c29f
issues-quality is a cursor rule published in the GitHub repository vepo/issues (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 613 tokens to every session, about $0.0031 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.
Other cursor rules, from other repositories
project-context
EDDI Backend — AI Agent Instructions. Complete project context, architecture, and coding guidelines.
testing-visual
Source: docs/agents/testing-visual.md Regenerate: npm run agents:sync -w packages/openbridge-webcomponents -->.
com-example-service-PublicPaymentController
AI rules for com.example.service.PublicPaymentController.
front-vue-page-conventions
YiSmartCloud front-end Vue page conventions.
cursorrules
Cursor rule "cursorrules" from Forge-Space/ui-mcp, covering uiforge mcp cursor rules, environment setup, development guidelines, component library integration and figma integration.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.