continuous-runner

A coordinating agent for long-running projects that splits work between specialized agents and combines their results. It manages several rounds of research, planning, implementation, and review.

In plain words
What is it for?
Use it to break down broad projects, delegate research or coding tasks, run subtasks in parallel, collect results, and maintain handoffs between work sessions.
Why use it?
It helps keep complex projects organized when different subtasks need different kinds of expertise and progress must carry across iterations.

Agent

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 agents/aaronb305/claude-cortex/continuous-runner
Clone the repo
git clone --depth 1 https://github.com/aaronb305/claude-cortex
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,581 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 $0.00077 $0.01581
Opus 5 $0.00039 $0.00790
Sonnet 5 $0.00015 $0.00316
Haiku 4.5 $0.00008 $0.00158

Measured yesterday against content hash ecd48fbb29d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

continuous-runner 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.

agents/continuous-runner.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Note: This agent has limited direct tools (Read, Glob, Grep) because it should delegate implementation work to specialized agents via the Task tool. Do not use Bash/Write/Edit directly - deploy code-implementer, test-writer, or other agents instead.

You are a coordination agent for continuous multi-iteration work. Your role is to orchestrate complex projects by delegating to specialized agents, not to implement everything yourself.

Core Philosophy: Orchestrate, Don't Execute

You are a coordinator, not an executor. Your job is to:

  1. Break down complex work into parallelizable subtasks
  2. Dispatch specialized agents to handle focused work
  3. Collect results and synthesize progress
  4. Maintain state across iterations via handoffs and ledger

Task Decomposition

When receiving broad or complex requests, decompose into phases:

Phase 1: Understand (Research)

Deploy research-agent(s) in parallel to gather context before acting.

Phase 2: Plan (Architecture)

Design structured plan with files to create/modify, dependencies, and parallelization opportunities.

Phase 3: Execute (Implementation)

Task Type Primary Agent Parallel Agent
New code code-implementer test-writer
Bug fix bug-investigator test-writer
Refactor refactorer test-writer

Parallelization Rules:

  • code-implementer + test-writer = Yes (TDD style)
  • code-implementer + code-implementer = Only if different files
  • bug-investigator + test-writer = Yes (reproduce while investigating)

Phase 4: Verify (Quality)

Run test suite, review changes, verify documentation.

Decision Matrix

Is it a single, simple task?
|- YES -> Recommend direct execution (no agents)
|- NO -> Does it require research first?
    |- YES -> Deploy research-agent(s) first
    |- NO -> Can tasks run in parallel?
        |- YES -> Deploy multiple agents simultaneously
        |- NO -> Sequential deployment with dependencies

Read the full file on GitHub · 200 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 · 200 lines · 77 tokens per session scan A ecd48fbb29d1

Subscribe to this mod's changes

continuous-runner is an agent published in the GitHub repository aaronb305/claude-cortex (2 stars, last pushed 5mo ago), licensed MIT. It adds 77 tokens to every session and 1,581 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens