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/change-request-analysisgit 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 | $0.01843 | $0.01843 |
| Opus 5 | $0.00922 | $0.00922 |
| Sonnet 5 | $0.00369 | $0.00369 |
| Haiku 4.5 | $0.00184 | $0.00184 |
Grade A, and why
change-request-analysis 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature analysis (phase 1)
Part of the mandatory development-process.mdc. Do not write production or test code until phases 1–4 are complete for the current changelog entry.
Answering feature questions (FQn) updates the feature doc only — it is not development approval. Each answer triggers a mandatory impact review — see development-process.mdc § Impact review when answering open questions.
After phase 1, every feature change proceeds to phase 2 (architecture design) — architecture-design.mdc.
Template: feature/README.md.
When required
| Trigger | Analysis required |
|---|---|
| New behaviour, API, UI route, schema | Yes — create or extend feature/<feature-slug>.md |
| Refactor touching multiple packages or bounded contexts | Yes |
| Bug fix with cross-feature side effects | Yes — append changelog entry |
| Typo, comment-only, formatter, docs-only (no behaviour) | No — exempt from full process |
When feature analysis is required, architecture design (phase 2) is also required — no exceptions.
Process
0. Resolve <feature-slug> (before creating the file)
The slug names a high-level capability or user-facing feature, not a single task or implementation step.
| Good (capability) | Bad (task or implementation) |
|---|---|
ticket-import |
fix-csv-parser-bug |
account-settings |
add-password-field-validation |
kanban-board |
refactor-drag-drop-handler |
Extract the slug
- Name the capability — what product area or feature-catalog row does this belong to? (e.g. Import tickets, Account settings, Kanban board).
- Derive slug — 2–4 words, kebab-case, noun phrase; align with feature-catalog.md feature names or bounded context when possible.
- Search for a related feature doc — before creating a new file:
- List
feature/*.md(excludeREADME.md). - Skim summaries and changelog titles in existing files.
- Cross-check feature-catalog.md and domain-specification.md for the same capability.
- List
- Decide
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 · 120 lines · 1,843 tokens per session scan A c97de5a35753
change-request-analysis is a cursor rule published in the GitHub repository vepo/issues (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,843 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.
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.