agents

Advanced agent delegation strategies for optimal workload distribution and specialized task execution. Defines when and how to delegate tasks to specialized coding agents, monitoring strategies, and integration patterns. Apply when: planning complex features, managing high workloads, requiring specialized expertise…

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

Made for: Cursor.

Per session 2,339 This file is loaded in full into every session.
When invoked 2,339 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 $0.02339 $0.02339
Opus 5 $0.01170 $0.01170
Sonnet 5 $0.00468 $0.00468
Haiku 4.5 $0.00234 $0.00234

Measured yesterday against content hash 6fb217989c1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agents 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/sample-realtime-chat/.cursor/rules/agents.mdc · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Delegation Strategy & Best Practices

1. Delegation Decision Framework

1.1 When to Delegate (DELEGATE)

Primary Criteria:

  • Complexity + Independence: Task is complex but doesn't require deep system integration
  • Specialized Expertise: Task benefits from focused domain expertise (testing, documentation, research)
  • Parallel Execution: Task can run alongside other work without conflicts
  • Clear Scope: Task has well-defined boundaries and acceptance criteria
  • Time Intensive: Task is time-consuming but routine (documentation, code review)

Examples of Delegation Candidates:

  • API documentation generation
  • Unit test implementation for specific components
  • Code review and refactoring of isolated modules
  • Research tasks (technology evaluation, pattern analysis)
  • Migration scripts for data transformations
  • Performance optimization for specific algorithms
  • Integration testing for external services

1.2 When to Execute Directly (EXECUTE)

Primary Criteria:

  • Strategic Decisions: Architectural choices, design patterns, technology selection
  • Deep Integration: Requires understanding of entire system context
  • User Interaction: Tasks requiring user feedback or iterative refinement
  • Security Sensitive: Authentication, authorization, data protection implementations
  • System Critical: Core framework functionality, essential business logic

Examples of Direct Execution:

  • Architecture design and planning
  • Core feature implementations requiring system-wide changes
  • Database schema design and migrations
  • Security implementations
  • User interface design and user experience decisions
  • Integration of delegated work into main system

1.3 Hybrid Approach (DELEGATE + SUPERVISE)

Suitable for:

  • Large features that can be broken into independent components
  • Research tasks that inform direct execution decisions
  • Code generation tasks that require review and integration
  • Testing tasks that validate direct implementations

Read the full file on GitHub · 281 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 · 281 lines · 2,339 tokens per session scan A 6fb217989c1c

Subscribe to this mod's changes

agents is a cursor rule published in the GitHub repository felipebarcelospro/igniter-js (242 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 2,339 tokens to every session, about $0.0117 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.