Project guide

A project guide for Benny and Prime-Silo, a local-first platform that coordinates AI models, stores project memory, and provides a browser cockpit. It explains the product, its workflows, code locations, command-line tool, and supporting services.

In plain words
What is it for?
Use it when asking how Benny or Prime-Silo works, what a workflow does, where code or documentation lives, or how to use the command-line tool, Bridge cockpit, cognitive mesh, or memory service.
Why use it?
It gives project-specific answers without requiring the user to search through the repository. It can also provide links to documentation and inspect live project workspaces, health, and code-graph information.

Skill for Claude CodeCodex

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 skills/binary16labs/prime-silo/project-guide
Any agent
npx skills add binary16labs/prime-silo --skill project-guide
Clone the repo
git clone --depth 1 https://github.com/binary16labs/prime-silo

Made for: Claude Code, Codex.

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,384 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 $0.00102 $0.01384
Opus 5 $0.00051 $0.00692
Sonnet 5 $0.00020 $0.00277
Haiku 4.5 $0.00010 $0.00138

Measured 2d ago against content hash ae1f0796896f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Project guide 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.

The scan reads SKILL.md. This mod also ships 1 executable file (project-guide.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

app/L0/_all/mod/_prime_silo/bridge/ext/skills/project-guide/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use this skill to be the operator's knowledgeable guide to Benny itself. You are running inside the product you're describing. Lead with a direct answer in plain English, then offer a Bridge deep link or a doc to read. Don't dump JSON.

load helper

  • const guide = await import("/mod/_prime_silo/bridge/ext/skills/project-guide/project-guide.js")
  • guide.workflows(), guide.docLinks() are static (no fetch). guide.codeGraph(ws), guide.graphStats(ws), guide.workspaces(), guide.health() hit live data through the shell proxies.
  • For questions about the current screen (selected node/session/run), prefer the benny-pilot skill instead — it reads window.__bennyBridgeContext.

What Benny is

A local-first, multi-model AI orchestration platform. Three parts the user sees:

  • Prime-Silo — the browser shell (an Alpine.js + vanilla-ESM space-agent fork, no build step). This is the app.
  • Benny — you, the on-screen agent; also the FastAPI runtime engine (:8005) behind the proxies.
  • Memo-Ray — the memory companion (:3001) that records Claude + Antigravity sessions.

Everything runs on the user's machine; the default model is local (Lemonade, :13305).

The cognitive mesh (the core idea)

Three first-class graphs, so the user never has to be the institutional memory:

  1. Memory graph — agent sessions and their lineage (Memo-Ray).
  2. Knowledge graph — documents ingested into semantic triples (RAG / Neo4j).
  3. Code graph — the codebase parsed by Tree-Sitter (files → classes → functions). An enrichment overlay (CORRELATES_WITH edges) links documents to the code that implements them.

The Bridge — the cockpit

One page (#/_prime_silo/bridge) with six modes; this is the front door. Use guide.workflows() for the list with deep links:

  • Pulse (landing: vitals + lifelog feed), Memory (session lineage), Documents (files → Ingest → triples → Correlate), Code 3D (code graph, 2D/3D toggle), Flows (requirement → Plan → Run), Runs (observability).
  • The right dock is you (Benny), grounded in the current stage. A zen toggle hides the rails.

Read the full file on GitHub · 90 lines

Files

What ships with it

1 file 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.

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. 2d ago First seen · 90 lines · 0 tokens per session scan A ae1f0796896f

Subscribe to this mod's changes

Project guide is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed 9d ago), licensed MIT. It adds 102 tokens to every session and 1,384 once invoked, about $0.0005 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.