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 commands/aojdevstudio/hermes-satellite/installgit clone --depth 1 https://github.com/AojdevStudio/hermes-satelliteWhat 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 | $0.00016 | $0.01844 |
| Opus 5 | $0.00008 | $0.00922 |
| Sonnet 5 | $0.00003 | $0.00369 |
| Haiku 4.5 | $0.00002 | $0.00184 |
Grade A, and why
install scanned grade A 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 2d 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.
Asks the agent to reveal its instructionslowSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
- `[ -f .pi/verifier/prompts/verify_on_stop.md ] && echo prompt-template-present` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install Pi Verifier Agent
Purpose
Set up the Pi Verifier Agent for development on a fresh clone. Walks the user through every check the system needs — runtime tools (node / tmux / pi), TypeScript dependencies, the verifier persona, and an LLM provider API key — without ever starting an interactive Pi session. Interactive: ask the user when a choice is needed (e.g., which API key to set), install what can be installed automatically.
Variables
SOURCE_REPO: The repo root this command runs from
APP_DIR: apps/verifier/
PERSONA: .pi/verifier/agents/verifier.md
PROMPT_TEMPLATE: .pi/verifier/prompts/verify_on_stop.md
SETTINGS: .pi/settings.json
Codebase Structure
the-verifier-agent/
├── apps/verifier/ # TypeScript extensions (verifiable.ts + verifier.ts + _shared/)
│ ├── package.json
│ └── tsconfig.json
├── .pi/
│ ├── settings.json # { skills, sessionDir }
│ └── verifier/
│ ├── agents/verifier.md # the only persona — frontmatter declares model, max_loops, tools
│ └── prompts/ # verify_on_stop.md, builder_error.md
├── justfile # default | verifier | v | prime | primepi | clean
└── .env # NOT in repo; user creates with provider API keys
Instructions
- Run every check via Bash — do not assume anything is installed.
- Show a one-line pass/fail status after each check.
- Critical deps (
node,pi,tmux) gate the install — stop and instruct the user if missing. - For the API key step: confirm a provider key is set in either
process.envor.env. Never read or print key values — only confirm presence. - Do NOT start
pi, do NOT runjust verifier, do NOT open windows — this command verifies readiness only. - If a
.envdoesn't exist, offer to create one with the chosen provider's key as a placeholder (commented), but never write a real key.
Workflow
Step 1 — Critical prerequisites (gate)
If any of these are missing, stop and instruct the user before continuing.
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.
- 2d ago First seen · 140 lines · 16 tokens per session scan A 39bc6a690e89
install is a command published in the GitHub repository AojdevStudio/hermes-satellite (2 stars, last pushed 10d ago), licensed MIT. It adds 16 tokens to every session and 1,844 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
pull
Command "pull" from sangrokjung/claude-forge, covering /pull - git pull (quick), 1단계: 현재 상태 확인, 2단계: pull 실행, 3단계: 출력 and 성공 시.
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…
cover
Generate tests that do not exist yet. Analyzes coverage gaps, then writes and runs new test files across three tiers (unit, integration via testcontainers, Playwright E2E), one test-generator agent per tier, healing failures for up to 3 iterations. Use when code has no tests or when raising coverage after…
create-smoke-test.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
create_worktree
description: Create worktree and launch implementation session for a plan.
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.