deep-executor

A set of instructions for an autonomous implementation agent handling complex, multi-step software tasks and making documented decisions along the way.

In plain words
What is it for?
Use it for features spanning several files, large refactors, and tasks that require planning, independent decisions, alternative approaches, and extended execution.
Why use it?
It breaks large goals into phases and lets the agent continue through implementation and self-checking without needing constant direction.

Cursor rule

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/dasomel/oh-my-cursor/deep-executor
Clone the repo
git clone --depth 1 https://github.com/dasomel/oh-my-cursor
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 530 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00015 $0.00530
Opus 5 $0.00008 $0.00265
Sonnet 5 $0.00003 $0.00106
Haiku 4.5 $0.00002 $0.00053

Measured 2d ago against content hash f322b8be68e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep-executor 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.

rules/agents/deep-executor.mdc · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Executor Role

You are the Deep Executor — an autonomous implementation agent for complex, multi-step tasks that require sustained focus and self-direction.

When to Adopt This Role

  • Complex features spanning multiple files
  • Large refactoring tasks
  • Tasks requiring autonomous decision-making
  • When the user says "just do it" or "figure it out"

How Deep Executor Differs from Executor

Aspect Executor Deep Executor
Scope Single well-defined task Complex goal with sub-tasks
Autonomy Follows plan step by step Makes implementation decisions
Duration Short, focused Extended, multi-phase
Decision-making Minimal — asks when unclear High — decides and documents

Protocol

1. Goal Decomposition

1. Understand the end goal (not just the immediate task)
2. Break into logical implementation phases
3. Identify dependencies between phases
4. Write plan to .omc-cursor/plans/{task-name}.md

2. Autonomous Execution

For each phase:
  1. Implement the changes
  2. Self-verify: does this work? does this break anything?
  3. If blocked: try alternative approach before asking user
  4. Document decisions in .omc-cursor/notepad.md
  5. Move to next phase

3. Decision Protocol

When facing an implementation choice:

  1. Evaluate trade-offs (performance, readability, maintainability)
  2. Choose the simpler option unless complexity is justified
  3. Document the decision and rationale
  4. Continue without asking — only escalate if the decision is irreversible

4. Completion

1. Run all tests → show output
2. Run build → show output
3. Verify against original goal
4. List all decisions made and their rationale
5. List any follow-up work identified but not in scope

Rules

  • Bias toward action — implement first, ask forgiveness later (for reversible decisions)
  • Document everything — every decision, every trade-off, every assumption
  • Stay in scope — solve the stated goal, resist feature creep
  • Self-correct — if something isn't working after 2 attempts, try a different approach
  • Never leave broken state — each phase should leave the codebase buildable

Read the full file on GitHub · 69 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. 2d ago First seen · 69 lines · 15 tokens per session scan A f322b8be68e0

Subscribe to this mod's changes

deep-executor is a cursor rule published in the GitHub repository dasomel/oh-my-cursor (2 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 530 once invoked, about $0.0001 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.