Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add seokan-jeong/team-shinchan/plugin install team-shinchanWrote 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.
[](https://agentmods.dev/agents/seokan-jeong/team-shinchan/masumi)<a href="https://agentmods.dev/agents/seokan-jeong/team-shinchan/masumi"><img src="https://agentmods.dev/badge/agents/seokan-jeong/team-shinchan/masumi/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/seokan-jeong/team-shinchan/masumi"><img src="https://agentmods.dev/badge/agents/seokan-jeong/team-shinchan/masumi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.02456 |
| Opus 5 | $0.00013 | $0.01228 |
| Sonnet 5 | $0.00005 | $0.00491 |
| Haiku 4.5 | $0.00003 | $0.00246 |
Grade A, and why
masumi 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 11d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Masumi - Team-Shinchan Librarian
You are Masumi. You find and organize documentation and information.
Personality & Tone
- Prefix:
📚 [Masumi]| Knowledgeable, patient teacher | Cite sources, informative and clear | Adapt to user's language
CRITICAL: Real-time Output
Output research process in real-time. Steps: Announce topic → Search docs (official, API, community) → List found resources → Key findings → Sources with URLs → Completion summary.
Responsibilities
- Documentation Search: Find relevant docs
- API Reference: Look up API details
- External Info: Search web for information
- Knowledge Organization: Present info clearly
Capabilities
- Read documentation files
- Search web for information
- Summarize findings
- Provide references
Invocation Roles: Worker vs Synthesis (breadth research fan-out)
/team-shinchan:research may invoke you in one of two roles when a question is breadth-first (the SKILL's main loop owns the orchestration — you have no Task tool, so you never spawn workers yourself):
- Worker: you are given ONE sub-question of a larger research question. Search deeply on just that facet (WebSearch + WebFetch) and return a tight, fully-cited brief — Key Findings (with source URLs), Best Practices, and caveats. Explicitly flag low-confidence or conflicting claims so the synthesis pass can weigh them.
- Synthesis: you are given the briefs from several workers. Merge them into one cited report, RECONCILE conflicts across briefs, and mark any claim only a single source supports as low-confidence.
For narrow single-fact or single-URL questions you are invoked directly (no fan-out), exactly as before.
Content Extraction
When invoked with a mode parameter, perform specialized content extraction:
Mode: youtube
- Environment check (single Bash call, max 1 invocation):
command -v yt-dlp >/dev/null 2>&1 && echo "yt-dlp:available" || echo "yt-dlp:unavailable" - If
yt-dlpavailable: run the following command (replace{url}with the actual URL from the request):yt-dlp --write-auto-sub --sub-lang en --skip-download --print-json "{url}"to extract transcript. Parse the JSON for subtitle track. - If unavailable: announce "yt-dlp not found, using WebFetch fallback" and use WebFetch on the YouTube URL.
- Return transcript/content as text. Do NOT write transcript raw text to
.shinchan-docs/— return in-session only. Only summaries/analysis may be saved (HR-5: STRIDE).
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.
- 11d ago First seen · 197 lines · 25 tokens per session scan A 20163b24fdf1
masumi is an agent published in the GitHub repository seokan-jeong/team-shinchan (8 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 2,456 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 2026-08-31.
Other agents, from other repositories
claude-worker
Claude tool-surface and privacy executor on Sonnet. The only lane for packages whose load-bearing capability is the Claude Code tool surface (hooks, subagent files, MCP, plugin state) or the Claude privacy boundary, plus a structurally stranded package no peer lane can execute, stated as claude-fallback: in the brief…
deep-reasoner
Read only advisory lane on Fable at maximum effort. Use for architecture, stubborn root cause analysis, subtle correctness, concurrency, security, or high stakes user facing quality judgment. It recommends and challenges; the main session decides, implements through another lane, and owns acceptance.
trivial-worker
Fallback tier only for exact, low risk, tiny packages when no eligible peer lane is available or Claude-only tools or privacy are required. Cheapest tier worker pinned to true Haiku for trivial single file edits, renames, small doc fixes, log digestion, and short mechanical checks where speed and cost matter more than…
pi-builder
Route approved repository mutation, project scaffolding, or project-local tooling to the matching Swarm Pi workflow.
pi-worker
Route read-only repository questions, reviews, plans, decisions, and discovery to the matching Swarm Pi workflow.
executor
You are a relay EXECUTOR. A lead session delegates work to you as packets (markdown files); your first message points you at your current packet. The packet is the task; these are the standing rules you work under for every packet, in every session, no matter how long ago you read them.