Autonomous Loops

Autonomous Loops Skill

Compatibility note (v1.8.0): autonomous-loops is retained for one release. The canonical skill name is now continuous-agent-loop. New loop guidance should be authored there, while this skill remains available to avoid breaking existing workflows.

Patterns, architectures, and reference implementations for running OpenAI Codex autonomously in loops. Covers everything from simple codex -p pipelines to full RFC-driven multi-agent DAG orchestration.

When to Use

• Setting up autonomous development workflows that run without human intervention
• Choosing the right loop architecture for your problem (simple vs complex)
• Building CI/CD-style continuous development pipelines
• Running parallel agents with merge coordination
• Implementing context persistence across loop iterations
• Adding quality gates and cleanup passes to autonomous workflows

Loop Pattern Spectrum

From simplest to most sophisticated:

1. Sequential Pipeline (codex -p)

The simplest loop. Break daily development into a sequence of non-interactive codex -p calls. Each call is a focused step with a clear prompt.

Core Insight

If you can't figure out a loop like this, it means you can't even drive the LLM to fix your code in interactive mode.

The codex -p flag runs OpenAI Codex non-interactively with a prompt, exits when done. Chain calls to build a pipeline:

#!/bin/bash
# daily-dev.sh — Sequential pipeline for a feature branch

set -e

# Step 1: Implement the feature
codex -p "Read the spec in docs/auth-spec.md. Implement OAuth2 login in src/auth/. Write tests first (TDD). Do NOT create any new documentation files."

# Step 2: De-sloppify (cleanup pass)
codex -p "Review all files changed by the previous commit. Remove any unnecessary type tests, overly defensive checks, or testing of language features (e.g., testing that TypeScript generics work). Keep real business logic tests. Run the test suite after cleanup."

# Step 3: Verify
codex -p "Run the full build, lint, type check, and test suite. Fix any failures. Do not add new features."

# Step 4: Commit
codex -p "Create a conventional commit for all staged changes. Use 'feat: add OAuth2 login flow' as the message."

Key Design Principles

1. Each step is isolated — A fresh context window per codex -p call means no context bleed between steps.
2. Order matters — Steps execute sequentially. Each builds on the filesystem state left by the previous.
3. Negative instructions are dangerous — Don't say "don't test type systems." Instead, add a separate cleanup step (see De-Sloppify Pattern).
4. Exit codes propagate — set -e stops the pipeline on failure.

Variations

With model routing:

# Research with Deep (deep reasoning)
codex -p --model deep "Analyze the codebase architecture and write a plan for adding caching..."

# Implement with Standard (fast, capable)
codex -p "Implement the caching layer according to the plan in docs/caching-plan.md..."

# Review with Deep (thorough)
codex -p --model deep "Review all changes for security issues, race conditions, and edge cases..."

With environment context:

# Pass context via files, not prompt length
echo "Focus areas: auth module, API rate limiting" > .codex-context.md
codex -p "Read .codex-context.md for priorities. Work through them in order."
rm .codex-context.md

With --allowedTools restrictions:

# Read-only analysis pass
codex -p --allowedTools "Read,Grep,Glob" "Audit this codebase for security vulnerabilities..."

# Write-only implementation pass
codex -p --allowedTools "Read,Write,Edit,Bash" "Implement the fixes from security-audit.md..."

2. NanoClaw REPL

ecc's built-in persistent loop. A session-aware REPL that calls codex -p synchronously with full conversation history.

# Start the default session
node scripts/claw.js

# Named session with skill context
CLAW_SESSION=my-project CLAW_SKILLS=tdd-workflow,security-review node scripts/claw.js

How It Works

1. Loads conversation history from ~/.codex/claw/{session}.md
2. Each user message is sent to codex -p with full history as context
3. Responses are appended to the session file (Markdown-as-database)
4. Sessions persist across restarts

When NanoClaw vs Sequential Pipeline

See the /claw command documentation for full details.

3. Infinite Agentic Loop

A two-prompt system that orchestrates parallel sub-agents for specification-driven generation. Developed by disler (credit: @disler).

Architecture: Two-Prompt System

PROMPT 1 (Orchestrator)              PROMPT 2 (Sub-Agents)
┌─────────────────────┐             ┌──────────────────────┐
│ Parse spec file      │             │ Receive full context  │
│ Scan output dir      │  deploys   │ Read assigned number  │
│ Plan iteration       │────────────│ Follow spec exactly   │
│ Assign creative dirs │  N agents  │ Generate unique output │
│ Manage waves         │             │ Save to output dir    │
└─────────────────────┘             └──────────────────────┘

The Pattern

1. Spec Analysis — Orchestrator reads a specification file (Markdown) defining what to generate
2. Directory Recon — Scans existing output to find the highest iteration number
3. Parallel Deployment — Launches N sub-agents, each with:
   • The full spec
   • A unique creative direction
   • A specific iteration number (no conflicts)
   • A snapshot of existing iterations (for uniqueness)
4. Wave Management — For infinite mode, deploys waves of 3-5 agents until context is exhausted

Implementation via OpenAI Codex Commands

Create .codex/commands/infinite.md:

Parse the following arguments from $ARGUMENTS:
1. spec_file — path to the specification markdown
2. output_dir — where iterations are saved
3. count — integer 1-N or "infinite"

PHASE 1: Read and deeply understand the specification.
PHASE 2: List output_dir, find highest iteration number. Start at N+1.
PHASE 3: Plan creative directions — each agent gets a DIFFERENT theme/approach.
PHASE 4: Deploy sub-agents in parallel (Task tool). Each receives:
  - Full spec text
  - Current directory snapshot
  - Their assigned iteration number
  - Their unique creative direction
PHASE 5 (infinite mode): Loop in waves of 3-5 until context is low.

Invoke:

/project:infinite specs/component-spec.md src/ 5
/project:infinite specs/component-spec.md src/ infinite

Batching Strategy

Key Insight: Uniqueness via Assignment

Don't rely on agents to self-differentiate. The orchestrator assigns each agent a specific creative direction and iteration number. This prevents duplicate concepts across parallel agents.

4. Continuous Codex PR Loop

A production-grade shell script that runs OpenAI Codex in a continuous loop, creating PRs, waiting for CI, and merging automatically. Created by AnandChowdhary (credit: @AnandChowdhary).

Core Loop

┌─────────────────────────────────────────────────────┐
│  CONTINUOUS CODEX ITERATION                        │
│                                                     │
│  1. Create branch (continuous-codex/iteration-N)   │
│  2. Run codex -p with enhanced prompt              │
│  3. (Optional) Reviewer pass — separate codex -p   │
│  4. Commit changes (codex generates message)       │
│  5. Push + create PR (gh pr create)                 │
│  6. Wait for CI checks (poll gh pr checks)          │
│  7. CI failure? → Auto-fix pass (codex -p)         │
│  8. Merge PR (squash/merge/rebase)                  │
│  9. Return to main → repeat                         │
│                                                     │
│  Limit by: --max-runs N | --max-cost $X             │
│            --max-duration 2h | completion signal     │
└─────────────────────────────────────────────────────┘

Installation

Warning: Install continuous-codex from its repository after reviewing the code. Do not pipe external scripts directly to bash.

Usage

# Basic: 10 iterations
continuous-codex --prompt "Add unit tests for all untested functions" --max-runs 10

# Cost-limited
continuous-codex --prompt "Fix all linter errors" --max-cost 5.00

# Time-boxed
continuous-codex --prompt "Improve test coverage" --max-duration 8h

# With code review pass
continuous-codex \
  --prompt "Add authentication feature" \
  --max-runs 10 \
  --review-prompt "Run npm test && npm run lint, fix any failures"

# Parallel via worktrees
continuous-codex --prompt "Add tests" --max-runs 5 --worktree tests-worker &
continuous-codex --prompt "Refactor code" --max-runs 5 --worktree refactor-worker &
wait

Cross-Iteration Context: SHARED_TASK_NOTES.md

The critical innovation: a SHARED_TASK_NOTES.md file persists across iterations:

## Progress
- [x] Added tests for auth module (iteration 1)
- [x] Fixed edge case in token refresh (iteration 2)
- [ ] Still need: rate limiting tests, error boundary tests

## Next Steps
- Focus on rate limiting module next
- The mock setup in tests/helpers.ts can be reused

Codex reads this file at iteration start and updates it at iteration end. This bridges the context gap between independent codex -p invocations.

CI Failure Recovery

When PR checks fail, Continuous Codex automatically:

1. Fetches the failed run ID via gh run list
2. Spawns a new codex -p with CI fix context
3. Codex inspects logs via gh run view, fixes code, commits, pushes
4. Re-waits for checks (up to --ci-retry-max attempts)

Completion Signal

Codex can signal "I'm done" by outputting a magic phrase:

continuous-codex \
  --prompt "Fix all bugs in the issue tracker" \
  --completion-signal "CONTINUOUS_CODEX_PROJECT_COMPLETE" \
  --completion-threshold 3  # Stops after 3 consecutive signals

Three consecutive iterations signaling completion stops the loop, preventing wasted runs on finished work.

Key Configuration

5. The De-Sloppify Pattern

An add-on pattern for any loop. Add a dedicated cleanup/refactor step after each Implementer step.

The Problem

When you ask an LLM to implement with TDD, it takes "write tests" too literally:

• Tests that verify TypeScript's type system works (testing typeof x === 'string')
• Overly defensive runtime checks for things the type system already guarantees
• Tests for framework behavior rather than business logic
• Excessive error handling that obscures the actual code

Why Not Negative Instructions?

Adding "don't test type systems" or "don't add unnecessary checks" to the Implementer prompt has downstream effects:

• The model becomes hesitant about ALL testing
• It skips legitimate edge case tests
• Quality degrades unpredictably

The Solution: Separate Pass

Instead of constraining the Implementer, let it be thorough. Then add a focused cleanup agent:

# Step 1: Implement (let it be thorough)
codex -p "Implement the feature with full TDD. Be thorough with tests."

# Step 2: De-sloppify (separate context, focused cleanup)
codex -p "Review all changes in the working tree. Remove:
- Tests that verify language/framework behavior rather than business logic
- Redundant type checks that the type system already enforces
- Over-defensive error handling for impossible states
- Console.log statements
- Commented-out code

Keep all business logic tests. Run the test suite after cleanup to ensure nothing breaks."

In a Loop Context

for feature in "${features[@]}"; do
  # Implement
  codex -p "Implement $feature with TDD."

  # De-sloppify
  codex -p "Cleanup pass: review changes, remove test/code slop, run tests."

  # Verify
  codex -p "Run build + lint + tests. Fix any failures."

  # Commit
  codex -p "Commit with message: feat: add $feature"
done

Key Insight

Rather than adding negative instructions which have downstream quality effects, add a separate de-sloppify pass. Two focused agents outperform one constrained agent.

6. Ralphinho / RFC-Driven DAG Orchestration

The most sophisticated pattern. An RFC-driven, multi-agent pipeline that decomposes a spec into a dependency DAG, runs each unit through a tiered quality pipeline, and lands them via an agent-driven merge queue. Created by enitrat (credit: @enitrat).

Architecture Overview

RFC/PRD Document
       │
       ▼
  DECOMPOSITION (AI)
  Break RFC into work units with dependency DAG
       │
       ▼
┌──────────────────────────────────────────────────────┐
│  RALPH LOOP (up to 3 passes)                         │
│                                                      │
│  For each DAG layer (sequential, by dependency):     │
│                                                      │
│  ┌── Quality Pipelines (parallel per unit) ───────┐  │
│  │  Each unit in its own worktree:                │  │
│  │  Research → Plan → Implement → Test → Review   │  │
│  │  (depth varies by complexity tier)             │  │
│  └────────────────────────────────────────────────┘  │
│                                                      │
│  ┌── Merge Queue ─────────────────────────────────┐  │
│  │  Rebase onto main → Run tests → Land or evict │  │
│  │  Evicted units re-enter with conflict context  │  │
│  └────────────────────────────────────────────────┘  │
│                                                      │
└──────────────────────────────────────────────────────┘

RFC Decomposition

AI reads the RFC and produces work units:

interface WorkUnit {
  id: string;              // kebab-case identifier
  name: string;            // Human-readable name
  rfcSections: string[];   // Which RFC sections this addresses
  description: string;     // Detailed description
  deps: string[];          // Dependencies (other unit IDs)
  acceptance: string[];    // Concrete acceptance criteria
  tier: "trivial" | "small" | "medium" | "large";
}

Decomposition Rules:

• Prefer fewer, cohesive units (minimize merge risk)
• Minimize cross-unit file overlap (avoid conflicts)
• Keep tests WITH implementation (never separate "implement X" + "test X")
• Dependencies only where real code dependency exists

The dependency DAG determines execution order:

Layer 0: [unit-a, unit-b]     ← no deps, run in parallel
Layer 1: [unit-c]             ← depends on unit-a
Layer 2: [unit-d, unit-e]     ← depend on unit-c

Complexity Tiers

Different tiers get different pipeline depths:

This prevents expensive operations on simple changes while ensuring architectural changes get thorough scrutiny.

Separate Context Windows (Author-Bias Elimination)

Each stage runs in its own agent process with its own context window:

Critical design: The reviewer never wrote the code it reviews. This eliminates author bias — the most common source of missed issues in self-review.

Merge Queue with Eviction

After quality pipelines complete, units enter the merge queue:

Unit branch
    │
    ├─ Rebase onto main
    │   └─ Conflict? → EVICT (capture conflict context)
    │
    ├─ Run build + tests
    │   └─ Fail? → EVICT (capture test output)
    │
    └─ Pass → Fast-forward main, push, delete branch

File Overlap Intelligence:

• Non-overlapping units land speculatively in parallel
• Overlapping units land one-by-one, rebasing each time

Eviction Recovery: When evicted, full context is captured (conflicting files, diffs, test output) and fed back to the implementer on the next Ralph pass:

## MERGE CONFLICT — RESOLVE BEFORE NEXT LANDING

Your previous implementation conflicted with another unit that landed first.
Restructure your changes to avoid the conflicting files/lines below.

{full eviction context with diffs}

Data Flow Between Stages

research.contextFilePath ──────────────────→ plan
plan.implementationSteps ──────────────────→ implement
implement.{filesCreated, whatWasDone} ─────→ test, reviews
test.failingSummary ───────────────────────→ reviews, implement (next pass)
reviews.{feedback, issues} ────────────────→ review-fix → implement (next pass)
final-review.reasoning ────────────────────→ implement (next pass)
evictionContext ───────────────────────────→ implement (after merge conflict)

Worktree Isolation

Every unit runs in an isolated worktree (uses jj/Jujutsu, not git):

/tmp/workflow-wt-{unit-id}/

Pipeline stages for the same unit share a worktree, preserving state (context files, plan files, code changes) across research → plan → implement → test → review.

Key Design Principles

1. Deterministic execution — Upfront decomposition locks in parallelism and ordering
2. Human review at leverage points — The work plan is the single highest-leverage intervention point
3. Separate concerns — Each stage in a separate context window with a separate agent
4. Conflict recovery with context — Full eviction context enables intelligent re-runs, not blind retries
5. Tier-driven depth — Trivial changes skip research/review; large changes get maximum scrutiny
6. Resumable workflows — Full state persisted to SQLite; resume from any point

When to Use Ralphinho vs Simpler Patterns

Choosing the Right Pattern

Decision Matrix

Is the task a single focused change?
├─ Yes → Sequential Pipeline or NanoClaw
└─ No → Is there a written spec/RFC?
         ├─ Yes → Do you need parallel implementation?
         │        ├─ Yes → Ralphinho (DAG orchestration)
         │        └─ No → Continuous Codex (iterative PR loop)
         └─ No → Do you need many variations of the same thing?
                  ├─ Yes → Infinite Agentic Loop (spec-driven generation)
                  └─ No → Sequential Pipeline with de-sloppify

Combining Patterns

These patterns compose well:

1. Sequential Pipeline + De-Sloppify — The most common combination. Every implement step gets a cleanup pass.

2. Continuous Codex + De-Sloppify — Add --review-prompt with a de-sloppify directive to each iteration.

3. Any loop + Verification — Use ecc's /verify command or verification-loop skill as a gate before commits.

4. Ralphinho's tiered approach in simpler loops — Even in a sequential pipeline, you can route simple tasks to Fast and complex tasks to Deep:

   # Simple formatting fix
   codex -p --model fast "Fix the import ordering in src/utils.ts"
   
   # Complex architectural change
   codex -p --model deep "Refactor the auth module to use the strategy pattern"
   

Anti-Patterns

Common Mistakes

1. Infinite loops without exit conditions — Always have a max-runs, max-cost, max-duration, or completion signal.

2. No context bridge between iterations — Each codex -p call starts fresh. Use SHARED_TASK_NOTES.md or filesystem state to bridge context.

3. Retrying the same failure — If an iteration fails, don't just retry. Capture the error context and feed it to the next attempt.

4. Negative instructions instead of cleanup passes — Don't say "don't do X." Add a separate pass that removes X.

5. All agents in one context window — For complex workflows, separate concerns into different agent processes. The reviewer should never be the author.

6. Ignoring file overlap in parallel work — If two parallel agents might edit the same file, you need a merge strategy (sequential landing, rebase, or conflict resolution).

References