A context-loading command for the Pi Verifier Agent, a two-process system where one process builds code and another observes it and runs read-only checks. It reads the project overview and the TypeScript files that implement this setup.

Use it at the start of a session to inspect the repository, architecture, state flow, socket communication, process launcher, configuration helpers, and verifier behavior.

It gives the agent a shared understanding of the runtime, current build state, communication between processes, and known limitations before work begins.

prime — Command for Claude Code by AojdevStudio: A context-loading command for the Pi Verifier Agent, a…

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 commands/aojdevstudio/hermes-satellite/prime

Clone the repo

git clone --depth 1 https://github.com/AojdevStudio/hermes-satellite

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/aojdevstudio/hermes-satellite/prime.svg)](https://agentmods.dev/commands/aojdevstudio/hermes-satellite/prime)

Your own site

<a href="https://agentmods.dev/commands/aojdevstudio/hermes-satellite/prime"><img src="https://agentmods.dev/badge/commands/aojdevstudio/hermes-satellite/prime.svg" alt="Measured on agentmods" height="20"></a>

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 420 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.

Model	Per session	Once invoked
Fable 5	$0.00015	$0.00420
Opus 5	$0.00008	$0.00210
Sonnet 5	$0.00003	$0.00084
Haiku 4.5	$0.00002	$0.00042

Measured 3d ago against content hash 69e0558938a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prime 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 3d 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.

.claude/commands/prime.md · 28 lines

What it actually says

Purpose

A two-process Pi system: a Builder Pi spawns a sibling Verifier Pi (in tmux) that observes builder turns and runs read-only verification with a generic verifier persona. This command orients you on the runtime and current build state.

Workflow

Run git ls-files to see what's tracked.
Read the public doc:
- README.md — install, quick-start, architecture overview, direction matrix, state machine, limitations
Read the runtime TypeScript (use the Read tool on each):
- apps/verifier/verifiable.ts — builder side: socket server, lifecycle event forwarding, prompt receipt
- apps/verifier/verifier.ts — verifier side: input lock, socket client, verifier_prompt tool, Report parser
- apps/verifier/verifiable-footer.ts — BuilderInputEditor (model/ctx/verifier-status in input border)
- apps/verifier/_shared/ipc.ts — envelope union types + JSONL framing
- apps/verifier/_shared/launcher.ts — $TMUX-aware spawn + wrapper-script (sidesteps macOS ARG_MAX)
- apps/verifier/_shared/frontmatter.ts — persona parser
- apps/verifier/_shared/socket-path.ts — socket path resolution (macOS 104-byte budget)
- apps/verifier/_shared/env.ts — env var helpers
Read the persona contract:
- .pi/verifier/agents/verifier.md — persona (CONFIDENCE ladder, atomic-decomposition)
- .pi/verifier/prompts/verify_on_stop.md — per-cycle user prompt template
Read justfile for runnable recipes (verifier, clean, prime).
Summarize your understanding of the project: purpose, stack, structure, key files, and entry points.

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.

3d ago First seen · 28 lines · 15 tokens per session scan A 69e0558938a7

Subscribe to this mod's changes

prime is a command published in the GitHub repository AojdevStudio/hermes-satellite (2 stars, last pushed 12d ago), licensed MIT. It adds 15 tokens to every session and 420 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.

Building agents agents hermes macos mcp verification

prime

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Purpose

Workflow

What this file has done since we first saw it

Other commands, from other repositories

app

mcp

move

set-value

merge-and-status

fix