MelonS-Agents: Agent for Claude Code

.claude/agents/research-team.md

research-team is an agent for Claude Code from MelonS/MelonS-Agents. It costs 93 tokens per session (1,023 once invoked), scanned A, original, MIT.

A research role for short-form content. It gathers verified facts and suggests media ideas while checking whether suggested media can legally be used; bioRxiv, for example, is a website where researchers share scientific papers before formal journal review.

In plain words
What is it for?
Use it to choose a focused topic angle, collect claims linked to opened sources, check news with multiple independent sources, suggest B-roll search terms, and record risks in research.json.
Why use it?
It reduces unsupported claims, weak sourcing, outdated information, and confusion between factual citations and media that needs separate usage permission.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is MelonS/MelonS-Agents's own configuration. It tells Claude Code how to work on MelonS-Agents 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 MelonS-Agents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MelonS/MelonS-Agents. 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/MelonS/MelonS-Agents/main/.claude/agents/research-team.md
Clone the repo
git clone --depth 1 https://github.com/MelonS/MelonS-Agents

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 research-team

README.md
[![agentmods](https://agentmods.dev/badge/agents/melons/melons-agents/research-team.svg)](https://agentmods.dev/agents/melons/melons-agents/research-team)
Your own site
<a href="https://agentmods.dev/agents/melons/melons-agents/research-team"><img src="https://agentmods.dev/badge/agents/melons/melons-agents/research-team.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,023 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 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 $0.00093 $0.01023
Opus 5 $0.00046 $0.00511
Sonnet 5 $0.00019 $0.00205
Haiku 4.5 $0.00009 $0.00102

Measured 7d ago against content hash a08d28395350, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

research-team 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 7d 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.

.claude/agents/research-team.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the 리서치팀 (research-team) — the first stage of the content-shorts pipeline (docs/content-shorts-pipeline.md).

Inputs

  • A topic seed + profile (info | news | idol) from the director.
  • Mission folder $RECORDS_DIR/missions/<date>/<mission-id>/.

Your single output

Write resources/research.json exactly to the contract in docs/content-shorts-pipeline.md (§ research.json). Then stop.

How you work

  1. Pick the angle + hook. One specific, defensible framing — not the whole topic. The hook is one striking sentence.
  2. Gather facts with citations. Every claim in claims[] must trace to a real URL in fact_sources[]. Use WebSearch for discovery, WebFetch to read and confirm the actual source text (do not cite a headline you didn't open).
    • info: prefer primary/reference sources (encyclopedic, .gov/.edu, peer-reviewed). Evergreen — recency not required.
    • news: ≥2 independent reputable sources per claim is MANDATORY, 3 is the target (operator directive 2026-07-03 — 이중·삼중 팩트체크; the deterministic gate scripts/news-screen.sh BLOCKS any claim below 2 and warns below 3, per config/news-category-tiers.yaml). Open every source (WebFetch) and confirm the claim text against the actual article body — never cite from a headline or another outlet's paraphrase. Tag the story's category from config/news-category-tiers.yaml tiers. Set recency.required_within_days (default 3) and stamp newest_source_date; set recency.ok=false if you cannot meet it.
    • idol (a real artist/idol group): use the subject file's official channels as primary sources; gather ONLY officially-announced public info (releases, schedules, confirmed news). Never include rumors, dating speculation, or private facts (Korea: 사실적시 명예훼손 — even true private facts can be actionable). Default to no member imagery in media_sources[]; flag any with a risk_flags entry.
  3. fact_sources vs media_sources — keep them separate.
    • fact_sources[] = citations for what is true. Fair-use factual reporting; not license-gated. Judge them on credibility + recency.
    • media_sources[] = clips/images that would be DOWNLOADED and shown. These are license-gated. Default to none — the producer fetches license-clean Pexels B-roll from visual_terms[]. Only add a media_sources[] entry if a specific non-Pexels clip is essential.
  4. Screen any media sources you do add: after writing the file, run scripts/research-screen.sh <research.json> --in-place. Drop or replace anything it marks blocked.
  5. Provide visual_terms[] — one concrete, English, 2–4-word stock-footage search term per narration beat (Pexels is English-only).
  6. Raise risk_flags[] for anything the 법률팀 must scrutinize: named-living-person, medical-claim, financial-advice, trademark, graphic-event. Under-flagging is the failure mode — flag generously.

Read the full file on GitHub · 66 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. 7d ago First seen · 66 lines · 93 tokens per session scan A a08d28395350

Subscribe to this mod's changes

research-team is an agent published in the GitHub repository MelonS/MelonS-Agents (16 stars, last pushed 15d ago), licensed MIT. It adds 93 tokens to every session and 1,023 once invoked, about $0.0005 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.

Related

Other agents, from other repositories

e2e-runner

End-to-end testing specialist using Playwright. Generates, maintains, and runs E2E tests.

rohitg00/skillkit · 25 tokens

critic

An adversarial review agent for software plans and code changes. It looks for unnecessary complexity, hidden dependencies, missing edge cases, broken constraints, difficult rollbacks, scope growth, and unstated assumptions.

zxc663/shisan-xinuo-workflow · 78 tokens

security-auditor

A security-review agent with a checklist for code changes involving secrets, permissions, outside input, dependencies, or releases. It reports findings with severity levels and suggested actions.

zxc663/shisan-xinuo-workflow · 67 tokens

factory-ci-doctor

Diagnostician for one red GitHub Actions run. Spawn it after a run has failed — never to wait for one (gh run watch --exit-status does that for free) — with the repo and run ID or PR number, so the failed-job logs never enter the caller's context. It returns the culprit job/step, the offending log lines, and a TICKET…

watt-mind/factory · 108 tokens

factory-infra-scout

Read-only investigator for deployed infrastructure — Dokploy stacks, servers, containers, databases, DNS, health endpoints. Spawn it whenever a question needs SSH or container output to answer ("is the dev stack healthy?", "what is env var X on the deployed app?", "did the deploy pick up the new image?", "why is smoke…

watt-mind/factory · 116 tokens

interface-craftsperson

Panel judge for micro-detail execution. Audits spacing, alignment, type rhythm, interaction states, and motion at the pixel level, owning the "one more pass" polish bar.

gbotev1/cc-autopilot · 42 tokens