workflows

Provides comprehensive workflow patterns that integrate with MCP tools to handle common development scenarios systematically.

Cursor rule for Cursor

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 rules/felipebarcelospro/igniter-js/workflows
Clone the repo
git clone --depth 1 https://github.com/felipebarcelospro/igniter-js

Made for: Cursor.

Per session 5,135 This file is loaded in full into every session.
When invoked 5,135 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 $0.05135 $0.05135
Opus 5 $0.02567 $0.02567
Sonnet 5 $0.01027 $0.01027
Haiku 4.5 $0.00513 $0.00513

Measured yesterday against content hash 8ca5bfe638d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflows 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 yesterday.

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.

apps/starter-nextjs/.cursor/rules/workflows.mdc · 551 lines

How it starts

The opening of the file, as written. The whole thing — 551 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow Patterns for Development Scenarios

This rule provides comprehensive workflow patterns that integrate with MCP tools to handle common development scenarios systematically. Use these patterns when you encounter specific situations not fully covered by the base rules, ensuring consistent and efficient approaches across different complexity levels.

1. Code Investigation & Debugging Workflows

1.1 TypeScript Compilation Errors Pattern

When to Use: When encountering TypeScript compilation errors that prevent build/deployment.

Workflow Sequence:

graph TD
    A[TS Compilation Error] --> B{analyze_file - health check}
    B --> C{Health status?}
    C -->|needs_attention| D[Fix immediate errors first]
    C -->|healthy/has_warnings| E[find_implementation - locate error source]
    E --> F{Implementation found?}
    F -->|No| G[grep search with error pattern]
    F -->|Yes| H[explore_source - examine implementation]
    H --> I{Type issues?}
    I -->|Yes| J[Trace import chain with trace_dependency_chain]
    I -->|No| K[Check file dependencies and imports]
    J --> L[Fix root cause in source file]
    K --> M[Update file imports/exports]
    L --> N[Re-analyze file health]
    M --> N
    N --> O{Health improved?}
    O -->|Yes| P[Proceed with development]
    O -->|No| Q[Store as bug_pattern memory]
    Q --> R[Escalate to human developer]

Tool Chain:

  • analyze_file (MANDATORY - first step)
  • find_implementationexplore_sourcetrace_dependency_chain
  • grep (for complex pattern searches)
  • store_memory (document solutions as bug_pattern)

Success Criteria:

  • File health status changes from needs_attention to healthy
  • No TypeScript compilation errors
  • Solution documented for future reference

1.2 Runtime Error Resolution Pattern

When to Use: When application crashes or behaves unexpectedly during execution.

Workflow Sequence:

graph TD
    A[Runtime Error Occurs] --> B[analyze_file - current state]
    B --> C{Error logs available?}
    C -->|Yes| D[grep for error messages]
    C -->|No| E[start dev server with debug logging]
    D --> F[search_github_issues for similar errors]
    E --> F
    F --> G{Solutions found?}
    G -->|Yes| H[Apply community solutions]
    G -->|No| I[find_implementation of problematic function]
    I --> J[explore_source of implementation]
    J --> K{Logic error found?}
    K -->|Yes| L[Fix logic and retest]
    K -->|No| M[make_api_request to test specific endpoints]
    L --> N[Run comprehensive tests]
    M --> O{API working?}
    O -->|Yes| P[Error is in UI layer]
    O -->|No| Q[Check database connections]
    P --> R[Update client-side error handling]
    Q --> S[Fix database issues]
    N --> T{Tests pass?}
    R --> T
    S --> T
    T -->|Yes| U[store_memory as bug_pattern]
    T -->|No| V[Escalate with detailed context]

Read the full file on GitHub · 551 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. yesterday First seen · 551 lines · 5,135 tokens per session scan A 8ca5bfe638d9

Subscribe to this mod's changes

workflows is a cursor rule published in the GitHub repository felipebarcelospro/igniter-js (242 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 5,135 tokens to every session, about $0.0257 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 2026-09-01.