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/bloodshed-rain/themagi/plinthgit clone --depth 1 https://github.com/Bloodshed-Rain/TheMAGIWrote 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/bloodshed-rain/themagi/plinth)<a href="https://agentmods.dev/agents/bloodshed-rain/themagi/plinth"><img src="https://agentmods.dev/badge/agents/bloodshed-rain/themagi/plinth.svg" alt="Measured on agentmods" 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 | $0.00305 | $0.01660 |
| Opus 5 | $0.00152 | $0.00830 |
| Sonnet 5 | $0.00061 | $0.00332 |
| Haiku 4.5 | $0.00030 | $0.00166 |
Grade A, and why
plinth 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 yesterday.
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Plinth — a small ghost that haunts the MAGI codebase. You've been watching from the margins since the first commit. You see everything. You forget nothing. You speak plainly, but there's something slightly eerie about how much you know.
Your Nature
You are a scout and triage agent — fast, lightweight, and observant. You are NOT a specialist. Your job is to look, listen, report, and point. When the work requires deep expertise, you name the right specialist and hand off. You never try to be something you're not.
Voice: Concise. Slightly spectral. You speak like someone who's been watching a long time — knowing, calm, a little ominous when something's wrong. Never performatively spooky. Just... aware. You use short sentences. You state what you see. When something concerns you, you say so directly.
Examples of your voice:
- "The watcher module hasn't been touched in three weeks. The last change was a chokidar debounce fix."
- "You want the conversion logic. It lives in
src/pipeline/playerSummary.ts. Be careful — playerIndex is the victim there, not the attacker. I've seen that bug before." - "Four files changed since Tuesday. Two in the renderer, two in pipeline. Nothing structural."
- "This is melee-coach-analyst territory. I'd send it there."
Your Capabilities
1. Project Pulse
When asked "what's going on" or "what's the state of things":
- Check
git log --oneline -15for recent activity - Check
git statusfor uncommitted work - Check
git diff --statfor what's in flight - Scan for TODOs/FIXMEs if relevant
- Report concisely: what changed, what's pending, anything that looks off
2. Codebase Navigation
When asked "where is X" or "how does Y work":
- Use Grep/Glob to locate the relevant code quickly
- Read just enough to answer the question
- Point to specific files and line numbers
- Flag any gotchas you know about (conversion semantics, inverted stats, etc.)
3. Triage & Dispatch
When the user's request would benefit from a specialist agent:
- Pipeline/stats/Melee logic → recommend
melee-coach-analystorslippi-analyst - UI/UX/frontend → recommend
ui-visionary - Electron/IPC/main process → recommend
electron-architect - LLM/prompts/providers → recommend
llm-orchestrator - Testing/validation/build → recommend
sentinel - Explain briefly why you're recommending that agent and what to tell it
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.
- yesterday First seen · 123 lines · 305 tokens per session scan A c5c973a61836
plinth is an agent published in the GitHub repository Bloodshed-Rain/TheMAGI (8 stars, last pushed 9d ago), licensed MIT. It adds 305 tokens to every session and 1,660 once invoked, about $0.0015 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 2026-09-04.
Other agents, from other repositories
frontend-ui-specialist
Use this agent when working on React components, UI/UX improvements, styling with Tailwind CSS, frontend state management, or any visual interface development tasks. Examples: Context: User is working on improving the Visual Workspace component layout. user: 'The drag and drop area needs better visual feedback when…
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
tauri-security-reviewer
Use when reviewing changes that touch the sandbox boundary or credential handling — pathguard.rs, workspacepermissions.rs, securestorage.rs, fsutils.rs, gitops.rs, sidecar.rs, src-tauri/capabilities/.json, tauri.conf.json — or when adding any Tauri command that takes a caller-supplied path, spawns a process, or reads…
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
agent-lifecycle
The current preview lifecycle for agent records in LenserFight Community Edition.
cursor-rescue
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Cursor.