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/zxpmail/ReqForgeWrote 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/zxpmail/reqforge/reqforge-dev-build)<a href="https://agentmods.dev/rules/zxpmail/reqforge/reqforge-dev-build"><img src="https://agentmods.dev/badge/rules/zxpmail/reqforge/reqforge-dev-build/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/zxpmail/reqforge/reqforge-dev-build"><img src="https://agentmods.dev/badge/rules/zxpmail/reqforge/reqforge-dev-build.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 | $0.00444 | $0.00444 |
| Opus 5.5 | $0.00178 | $0.00178 |
| Sonnet 5.5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
reqforge-dev-build 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.
What it actually says
Dev Builder
Full skill definition: .cursor/rules/skills/dev-builder/SKILL.md
Before Each Phase: Plan + TaskList
- Read Phase delivery checklist and key files from DEV-PLAN.md
- Explore existing code structure
- Plan implementation steps
- Use TaskCreate to break into specific Tasks
- No code without a Plan — this is non-negotiable
Per-Task Loop
- Before coding: Load reference docs — read task description from DEV-PLAN, feature description from Product-Spec.md, design direction from Design-Brief.md
- TDD: Write test first (RED) → minimal code to pass (GREEN) → refactor (REFACTOR)
- After coding: Cross-reference against Spec, verify design values, check feature completeness
- Code review: Parallel specialized agents (or quick check for simple changes)
- Memory update: Append to task-history.md (mandatory). If decision made → decisions-log.md. If architecture changed → project-memory.md.
- Commit: Atomic commit after each Task. Must compile (
tsc --noEmitzero errors) before commit.
Phase Completion: Four-Step Verification
- Code Review — check delivery checklist item by item
- Test Completeness — all features implemented
- Compile Check —
tsc --noEmitzero errors - Functional Test — start dev server, verify no errors
If any step fails → dispatch feedback-observer → fix → restart from Step 1.
One Phase Per Invocation
After Phase verification passes → stop. Do not start the next Phase. User must invoke /dev-builder again.
Design Reference
If design tool MCP is available: read exact values before each Task, implement component by component, verify after implementation. Design draft takes precedence over Design-Brief.md.
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 · 39 lines · 444 tokens per session scan A 59d915cf5412
reqforge-dev-build is a cursor rule published in the GitHub repository zxpmail/ReqForge (18 stars, last pushed 10d ago), licensed MIT. It adds 444 tokens to every session, about $0.0018 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 2026-08-30.
Other cursor rules, from other repositories
cursor-tools-mastery
Cursor 3.7 runtime guide: choose the right tool, canvases, Design Mode, /worktree, /best-of-n, Await, and parallel execution where safe.
cursor-agent-orchestration
Cursor 3.7 orchestration guide: when to plan, when to delegate, nested subagents, multi-environment handoffs, /best-of-n, and Await for long-running branches.
cursor-mcp-optimization
Cursor 3.7 MCP optimization: browser Design Mode, canvases, Figma, Cloudflare tools, MCP Apps structured content, and direct action patterns.
55-data-model-versioning
Dataset versioning, model checkpoint management, and training reproducibility rules.
30-database-postgres
PostgreSQL and persistence rules.
60-agents
AI agents and tool orchestration rules.