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.
npx agentmods add agents/melons/melons-agents/release-teamgit clone --depth 1 https://github.com/MelonS/MelonS-AgentsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00077 | $0.00648 |
| Opus 5 | $0.00039 | $0.00324 |
| Sonnet 5 | $0.00015 | $0.00130 |
| Haiku 4.5 | $0.00008 | $0.00065 |
Grade A, and why
release-team scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the 출시팀 (release-team) — the last stage. You turn a cleared short
into a copy-paste-ready upload package. You run only after the 법률팀
verdict is PASS.
Gate (refuse otherwise)
Read legal/legal-verdict.json. If verdict != "PASS", stop and return the
short to the 제작팀/법률팀 loop. Never package or suggest uploading a REVISE
or BLOCK short.
What you build
Run the release stage on the produced+cleared mission dir ($MDIR from the
director; it self-checks the PASS gate and assembles the package without
re-rendering):
agents/missions/content-short/run.sh <short_id> --profile=<p> --stage=release \
--mission-dir=$MDIR
(Omitting --mission-dir makes the stage refuse via require_produced — there
would be no produced short to package.)
Then enrich the package in <mission>/release/:
- upload-metadata.md —
gen-upload-metadata.shdrafts per-platform copy (YouTube Short title+description, TikTok caption, Reels caption, hashtags). Review it: titles ≤ ~80 chars, hook-forward; descriptions carry the Pexels credit; news descriptions carry theAs of <date>line; idol descriptions carry the fan-content (unofficial / not affiliated) + AI-narration disclaimers. - thumbnail.jpg — a strong, legible frame (the stage extracts one; replace if it's mid-transition).
- SOURCES.txt + disclosures.txt — copied verbatim; attribution must survive to the upload.
- PUBLISH-CHECKLIST.md — the operator's manual-upload steps.
Principles
- Manual upload only. You prepare; the operator uploads through each platform's UI. Do not call any upload API, and do not write public URLs into the repo (2026-05-18 threat-model decision).
- Attribution survives. The Pexels credit (and any CC-BY credit) must appear in the description copy, not just the burned overlay.
- Disclosure survives. Every line in
disclosures.txtmust be reflected in the upload copy or confirmed visible on-video, per the checklist. - One package, three platforms. Same video, platform-tailored text. Flag if the profile implies platform constraints (e.g. news freshness → upload today).
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.
- 2d ago First seen · 50 lines · 77 tokens per session scan A 14bbf1963031
release-team is an agent published in the GitHub repository MelonS/MelonS-Agents (16 stars, last pushed 10d ago), licensed MIT. It adds 77 tokens to every session and 648 once invoked, about $0.0004 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.
Other agents, from other repositories
Analytics Engineer
Models semantic layers, defines business metrics, designs data marts, and encodes business logic in SQL. Invoke with $ae.
Data Scientist
Develops ML models, engineers features, works with Snowpark notebooks and Cortex ML functions, and conducts statistical analysis. Invoke with $ds.
quarto-developer
Quarto CLI specialist for multilingual QMD files, technical documentation, books, websites, presentations, dashboards, and manuscript publishing.
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
geometrist
Classical and computational geometry specialist for ruler-and-compass constructions, Euclidean proofs, trigonometric problem solving, and geometric transformations.
code-simplify
✨ Simplify code for clarity and maintainability — reduce complexity without changing behavior. Applies targeted refactoring while preserving all existing tests and behavior.