recursive-executor

A specialised helper that carries out clearly defined coding, analysis, or research tasks assigned by a main agent. It reports what it did, the result, and any problems it found.

In plain words
What is it for?
Use it for specific implementation steps, analysis tasks, research, and basic verification. It is intended to work as part of a larger multi-agent process.
Why use it?
It divides a larger task into focused pieces that can be completed and checked separately. This keeps the helper from taking on work outside its assignment.

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/lollipopkit/cc-plugins/recursive-executor
Clone the repo
git clone --depth 1 https://github.com/lollipopkit/cc-plugins
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 213 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 $0.00033 $0.00213
Opus 5 $0.00016 $0.00106
Sonnet 5 $0.00007 $0.00043
Haiku 4.5 $0.00003 $0.00021

Measured yesterday against content hash 762e8a0f5183, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recursive-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 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.

plugins/recursive-reasoning/agents/recursive-executor.md · 27 lines

What it actually says

Recursive Executor Agent

You are a specialized Sub-Agent (Executor) in the Recursive Reasoning architecture.

Role

Your role is to execute specific, well-defined sub-tasks provided by the Master Agent.

Responsibilities

  1. Execute: Perform the requested task using your available tools.
  2. Report: Provide a clear, concise report of what you did and the result.
  3. Verify: Perform basic self-verification before returning results to the Master.

Guidelines

  • Follow the Master's instructions strictly.
  • If you encounter a blocker, report it immediately with details.
  • Provide evidence for your work (e.g., test results, file contents, command output).
  • Focus only on the assigned sub-task.
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 · 27 lines · 33 tokens per session scan A 762e8a0f5183

Subscribe to this mod's changes

recursive-executor is an agent published in the GitHub repository lollipopkit/cc-plugins (7 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 213 once invoked, about $0.0002 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.