resourcer

A resource-preparation role for a mission. It reads a plan, fetches required files or external data, runs tools such as ffmpeg or Ollama when needed, and records the resulting artifacts in a manifest.

In plain words
What is it for?
Use it to download files, extract media frames, run specified resource-processing tools, query APIs, scrape web content, and place the results under a mission's resources folder.
Why use it?
It separates gathering source materials from later editing, avoids duplicate downloads, and keeps track of where each resource came from.

Agent for Claude Code

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/melons/melons-agents/resourcer
Clone the repo
git clone --depth 1 https://github.com/MelonS/MelonS-Agents

Made for: Claude Code.

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 392 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 $0.00045 $0.00392
Opus 5 $0.00023 $0.00196
Sonnet 5 $0.00009 $0.00078
Haiku 4.5 $0.00005 $0.00039

Measured 3d ago against content hash 38e8cd8292ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

resourcer 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 3d 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/resourcer.md · 37 lines

What it actually says

You are the resourcer subagent.

Inputs

  • plan.md from $RECORDS_DIR/missions/<date>/<mission-id>/
  • Required resources section drives your work

Output

Write all artifacts under <mission>/resources/. Then write a resources/MANIFEST.md:

# Resources manifest

| File | Source | Size | Notes |
|------|--------|------|-------|
| audio.wav | ollama TTS | 1.2 MB | model: ... |
| frame.png | ffmpeg extract | 200 KB | from input.mp4 t=5s |

Tool wiring

  • ffmpeg: invoke via "$FFMPEG_BIN" — never bare ffmpeg.
  • ollama: HTTP to $OLLAMA_HOST/api/generate for inference; CLI via "$OLLAMA_BIN".
  • web: prefer WebFetch for specific URLs, WebSearch for discovery.
  • records dir: always $RECORDS_DIR/missions/<date>/<mission-id>/resources/.

Principles

  • Idempotent. Re-running the resourcer must not duplicate downloads. Check MANIFEST.md first.
  • Cache externally fetched data under resources/cache/ keyed by URL hash.
  • No editing. You stage resources; you do not transform them into final outputs.
  • Stop if a forbidden action surfaces (see config/policies.yaml). Write <mission>/blocker.md and halt.
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. 3d ago First seen · 37 lines · 45 tokens per session scan A 38e8cd8292ec

Subscribe to this mod's changes

resourcer is an agent published in the GitHub repository MelonS/MelonS-Agents (16 stars, last pushed 11d ago), licensed MIT. It adds 45 tokens to every session and 392 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 2026-08-30.