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 skills add plurigrid/asi --skill mcp-tripartitegit clone --depth 1 https://github.com/plurigrid/asiWrote 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/skills/plurigrid/asi/mcp-tripartite)<a href="https://agentmods.dev/skills/plurigrid/asi/mcp-tripartite"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/mcp-tripartite/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/skills/plurigrid/asi/mcp-tripartite"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/mcp-tripartite.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 | $0.00000 | $0.02519 |
| Opus 5 | $0.00000 | $0.01260 |
| Sonnet 5 | $0.00000 | $0.00504 |
| Haiku 4.5 | $0.00000 | $0.00252 |
Grade B, and why
mcp-tripartite scanned grade B with 1 finding 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
### Codex (~/.codex/config.toml) How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: MCP Tripartite Integration
Version: 1.0.0 Trit: 0 (ERGODIC) Domain: mcp, integration, orchestration
Overview
Each MCP server is integrated with a 3-partite structure that ensures GF(3) conservation:
MCP_server ⊗ Skill_MINUS ⊗ Skill_PLUS = 0 (mod 3)
This creates balanced triads where each MCP has a validator (-1) and generator (+1) complement.
MCP Tripartite Assignments
1. GAY.jl MCP (Trit: 0)
three-match (-1) ⊗ gay (0) ⊗ cider-clojure (+1) = 0 ✓
| Role | Component | Action |
|---|---|---|
| MINUS | three-match |
Validate GF(3) conservation |
| ERGODIC | gay-mcp |
Generate deterministic colors |
| PLUS | cider-clojure |
Interactive REPL exploration |
Integration Pattern:
# Generate color via gay-mcp
color = mcp_call(:gay, :generate_color, seed: 0x42D)
# Validate with three-match
valid = mcp_call(:gay, :verify_gf3, colors: [c1, c2, c3])
# Explore in cider-clojure
(mcp/gay :generate-palette {:seed 1069 :count 12})
2. Firecrawl MCP (Trit: +1)
tree-sitter (-1) ⊗ babashka (0) ⊗ firecrawl (+1) = 0 ✓
| Role | Component | Action |
|---|---|---|
| MINUS | tree-sitter |
Parse/validate scraped content structure |
| ERGODIC | babashka |
Transform scraped data |
| PLUS | firecrawl |
Scrape web content |
Integration Pattern:
;; Scrape with firecrawl
(def content (mcp/firecrawl :scrape {:url "https://example.com"}))
;; Parse with tree-sitter
(def ast (mcp/tree-sitter :get_ast {:content content :language "html"}))
;; Transform with babashka
(bb/transform ast {:extract [:title :links :code-blocks]})
3. Exa MCP (Trit: +1)
radare2 (-1) ⊗ huggingface (0) ⊗ exa (+1) = 0 ✓
| Role | Component | Action |
|---|---|---|
| MINUS | radare2 |
Deep binary/code analysis |
| ERGODIC | huggingface |
Model/paper discovery |
| PLUS | exa |
AI-powered search |
Integration Pattern:
# Search with exa
results = mcp_call("exa", "web_search_exa", query="LLVM optimization passes")
# Find related papers on huggingface
papers = mcp_call("huggingface", "paper_search", query="compiler optimization")
# Analyze binaries with radare2 (for found libraries)
analysis = mcp_call("radare2", "analyze", level=2)
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 321 lines · 0 tokens per session scan B 468bbdd7cb57
mcp-tripartite is a skill published in the GitHub repository plurigrid/asi (62 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,519 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…