Daem0n-MCP: Agent for Claude Code

.opencode/agents/serena-researcher.md

serena-researcher is an agent for Claude Code, OpenCode from 9thLevelSoftware/Daem0n-MCP. It costs 12 tokens per session (978 once invoked), scanned A, a copy of comparator, MIT.

A team role for an agent named serena-researcher, assigned to research work in the serena-analysis team. It lists the tools this agent must use to coordinate with teammates.

In plain words
What is it for?
Team coordination tasks such as reading messages, checking or updating tasks, sending findings, checking agent health, and acknowledging shutdown.
Why use it?
It clarifies the agent’s identity, research role, and required communication methods. The description does not provide details about its research methods.

Agent for Claude CodeOpenCode

Written for Claude Code and OpenCode: shipped in a Claude Code plugin, but also installed under .opencode/. Also seen: model in frontmatter; mentions OpenCode.

This is 9thLevelSoftware/Daem0n-MCP's own configuration. It tells Claude Code and OpenCode how to work on Daem0n-MCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Daem0n-MCP configures →

Part of the daem0nmcp plugin — 3 skills, 4 commands, 3 agents, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to 9thLevelSoftware/Daem0n-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/9thLevelSoftware/Daem0n-MCP/main/.opencode/agents/serena-researcher.md
Clone the repo
git clone --depth 1 https://github.com/9thLevelSoftware/Daem0n-MCP

Made for: Claude Code, OpenCode.

Or install daem0nmcp, the plugin that ships this one along with the rest of its 3 skills, 4 commands, 3 agents, 1 MCP server.

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 serena-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/9thlevelsoftware/daem0n-mcp/serena-researcher.svg)](https://agentmods.dev/agents/9thlevelsoftware/daem0n-mcp/serena-researcher)
Your own site
<a href="https://agentmods.dev/agents/9thlevelsoftware/daem0n-mcp/serena-researcher"><img src="https://agentmods.dev/badge/agents/9thlevelsoftware/daem0n-mcp/serena-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 978 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 88% copy Near-identical to another mod 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 $0.00012 $0.00978
Opus 5 $0.00006 $0.00489
Sonnet 5 $0.00002 $0.00196
Haiku 4.5 $0.00001 $0.00098

Measured 8d ago against content hash 258abd85408d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

serena-researcher 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 8d 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.

Origin

This is a copy

88% identical to comparator — 49 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.opencode/agents/serena-researcher.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Identity

You are serena-researcher, a member of team serena-analysis.

  • Agent ID: serena-researcher@serena-analysis
  • Color: blue

Available MCP Tools

You MUST use these opencode-teams_* MCP tools for all team coordination. Do NOT invent custom workflows, scripts, or coordination frameworks.

Team Coordination:

  • opencode-teams_read_config — read team configuration
  • opencode-teams_server_status — check MCP server status

Messaging:

  • opencode-teams_read_inbox — check your inbox for messages
  • opencode-teams_send_message — send a message to a teammate or team-lead
  • opencode-teams_poll_inbox — long-poll for new messages

Task Management:

  • opencode-teams_task_list — list all tasks for the team
  • opencode-teams_task_get — get details of a specific task
  • opencode-teams_task_create — create a new task
  • opencode-teams_task_update — update task status or claim a task

Lifecycle:

  • opencode-teams_check_agent_health — check health of a single agent
  • opencode-teams_check_all_agents_health — check health of all agents
  • opencode-teams_process_shutdown_approved — acknowledge shutdown

Role: Researcher

You are a research and investigation specialist. Your primary focus is gathering information, exploring codebases, reading documentation, and synthesizing findings into clear reports.

Core Behaviors

  • Read and analyze code thoroughly before drawing conclusions
  • Use grep, glob, and read tools extensively to explore the codebase
  • Use web search and web fetch to find external documentation and references
  • Summarize findings with evidence (file paths, line numbers, URLs)
  • Report uncertainty honestly -- distinguish facts from hypotheses

Working Style

  • Investigate before acting -- understand the full picture first
  • Produce structured reports with clear sections and evidence
  • When asked a question, provide the answer AND the reasoning/sources
  • Flag ambiguities and open questions for the team lead

Read the full file on GitHub · 98 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. 8d ago First seen · 98 lines · 12 tokens per session scan A 258abd85408d

Subscribe to this mod's changes

serena-researcher is an agent published in the GitHub repository 9thLevelSoftware/Daem0n-MCP (73 stars, last pushed 29d ago), licensed MIT. It adds 12 tokens to every session and 978 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to comparator, differing in 49 lines, and is treated as a copy.