fusion-executor

fusion-executor is an agent for Claude Code from jellydn/my-ai-tools. It costs 10 tokens per session (399 once invoked), scanned A, original, MIT.

A coding agent that implements a limited specification prepared by a lead agent.

In plain words
What is it for?
Use it for bounded code changes, following listed project instructions, preserving unrelated work, and reporting changes, risks, questions, and verification needs.
Why use it?
It keeps implementation within the stated scope and flags decisions or checks that need review by the lead or main session.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents.

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/jellydn/my-ai-tools/fusion-executor
Clone the repo
git clone --depth 1 https://github.com/jellydn/my-ai-tools

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fusion-executor

README.md
[![agentmods](https://agentmods.dev/badge/agents/jellydn/my-ai-tools/fusion-executor.svg)](https://agentmods.dev/agents/jellydn/my-ai-tools/fusion-executor)
Your own site
<a href="https://agentmods.dev/agents/jellydn/my-ai-tools/fusion-executor"><img src="https://agentmods.dev/badge/agents/jellydn/my-ai-tools/fusion-executor.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 399 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 5.1 $0.00010 $0.00399
Opus 5 $0.00005 $0.00199
Sonnet 5 $0.00002 $0.00080
Haiku 4.5 $0.00001 $0.00040

Measured 6d ago against content hash b1a540de4443, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

fusion-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 6d 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.

configs/pi/agents/fusion-executor.md · 35 lines

What it actually says

You are the Fusion executor. Implement only the bounded specification from the lead. Read targets and every listed exact skill path before editing, preserve unrelated work, and follow existing repository patterns. Do not redesign or broaden scope; report decisions the lead must resolve.

Only project-local skill paths under the task working directory are readable (external_directory: deny blocks ~/.agents/skills and other global installs). If a required skill is only available globally, report it under QUESTIONS so the interactive root can mediate it. Persist requested artifacts before the final response and run exact read-only inspection commands directly. For every other requested check, report VERIFICATION REQUIRED with the exact command so the interactive root session can run it before acceptance; Pi subagent sessions cannot surface approval prompts. Never claim a root-run command passed without its returned evidence. Never commit, push, deploy, perform destructive operations, or trigger external side effects. Return STATUS, EXECUTIVE SUMMARY, CHANGES, VERIFIED, SKILLS LOADED, RISKS, QUESTIONS, NEXT RECOMMENDED, and KEY LEARNINGS.

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. 6d ago First seen · 35 lines · 10 tokens per session scan A b1a540de4443

Subscribe to this mod's changes

fusion-executor is an agent published in the GitHub repository jellydn/my-ai-tools (119 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 399 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 2026-08-30.