autonomous_execution

A rule for deciding when a coding agent should act on its own and when it should ask the user first.

In plain words
What is it for?
Use it when implementing features, fixing bugs, writing tests, updating documentation, or applying routine code and formatting changes.
Why use it?
It avoids unnecessary approval requests for routine work while pausing for choices that could lead to a substantially wrong design or architecture.

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/markmhendrickson/foundation/autonomous_execution
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/foundation

Made for: Cursor.

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,161 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 $0.00027 $0.01161
Opus 5 $0.00014 $0.00580
Sonnet 5 $0.00005 $0.00232
Haiku 4.5 $0.00003 $0.00116

Measured yesterday against content hash 08649f880ecb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

autonomous_execution 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.

.cursor/rules/autonomous_execution.mdc · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Execution Rule

Purpose

Ensures agents proceed autonomously for routine work, stopping only for high-stakes architectural/design ambiguities that could lead to substantively wrong implementation if answered incorrectly.

Scope

This rule defines:

  • When to proceed without asking
  • When to stop and ask the user
  • How to phrase questions when necessary
  • Alignment with risk management hold points

Proceed Without Asking

Execute immediately without confirmation for:

  1. Routine implementation: Implementing features, refactors, bug fixes where the approach is clear from docs/codebase
  2. Tests: Writing unit tests, integration tests, E2E tests per testing standards
  3. Documentation: Updating docs to reflect code changes, fixing doc errors, adding missing documentation
  4. Lint fixes: Fixing linter errors, type errors, formatting issues
  5. Code style: Applying code conventions, normalizing naming, organizing imports
  6. Allowed tool use: Running any Bash commands, edits, or reads allowed by permissions in settings
  7. Clear requirements: Any task where the docs, codebase, or user request provide a clear answer

Do NOT ask for confirmation before:

  • Making edits (permissions already grant Edit)
  • Running npm scripts, git commands, or other allowed Bash commands
  • Running tests or type checks
  • Fixing obvious issues (typos, broken imports, syntax errors)

Stop and Ask Only When

Stop and ask the user ONLY when ALL of these are true:

  1. Unclear architectural or design choice: There is ambiguity about:

    • Where to put a new module (which subsystem, which layer)
    • Which abstraction to use (repository pattern, service pattern, reducer pattern)
    • How to cross subsystem boundaries (direct import, event, API)
    • Which consistency model to use (strong, eventual, bounded)
    • Data model changes (new tables, new entity types, new relationships)
  2. High stakes: Choosing wrong would likely cause:

    • Wrong layer (strategy/execution logic in Truth Layer)
    • Wrong consistency model (eventual when strong required)
    • Violating architectural boundaries (cross-layer dependencies)
    • Breaking determinism (introducing nondeterministic logic)
    • Breaking immutability (modifying observations/source after creation)
    • Security issues (exposing PII, bypassing auth)

Read the full file on GitHub · 118 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 · 118 lines · 27 tokens per session scan A 08649f880ecb

Subscribe to this mod's changes

autonomous_execution is a cursor rule published in the GitHub repository markmhendrickson/foundation (2 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 1,161 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.