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 instructions/ling-kong-ran/pisper/agents-mdgit clone --depth 1 https://github.com/ling-kong-ran/pisperWrote 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/instructions/ling-kong-ran/pisper/agents-md)<a href="https://agentmods.dev/instructions/ling-kong-ran/pisper/agents-md"><img src="https://agentmods.dev/badge/instructions/ling-kong-ran/pisper/agents-md.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 | $0.04109 | $0.04109 |
| Opus 5 | $0.02055 | $0.02055 |
| Sonnet 5 | $0.00822 | $0.00822 |
| Haiku 4.5 | $0.00411 | $0.00411 |
Grade A, and why
pisper AGENTS.md 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 today.
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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents working in the Pisper repository.
Project
Pisper is a multi-agent app across desktop, terminal, and mobile, built on Pi Coding Agent. It ships:
- a React web UI (dev server + production static assets)
- a Node.js app runtime / desktop sidecar that hosts sessions, tools, MCP, skills, memory, workflows, channels, and schedules
- a Tauri 2 desktop shell with a system WebView and a Node SEA sidecar
- a Rust Ratatui TUI client
Requires Node.js 20+ (desktop SEA packaging docs target Node 24). Runtime agent data defaults to ~/.pisper/agent (PISPER_AGENT_DIR overrides). Do not commit API keys, bot credentials, or personal data from that directory.
Architecture
| Path | Role |
|---|---|
src/ |
React + TypeScript frontend (Vite, Tailwind 4, shadcn/ui, Zustand, i18next) |
src/app/ |
App shell: routing, providers, i18n wiring, navigation |
src/features/ |
Feature pages (chat, config, skills, MCP/plugins, workflows, …) |
src/components/ui/ |
shadcn/ui primitives; prefer composing these over one-off styles |
src/locales/{zh-CN,en-US}/ |
Translation namespaces (namespace:key) |
runtime/ |
Node app runtime (plain ESM .mjs): HTTP API, agent integration, services, tools |
runtime/runtime/ |
Pi agent runtime integration |
runtime/services/ |
Domain services (sessions, MCP, schedules, workflows, providers, …) |
runtime/tools/app/ |
Application-level agent tools (one module per tool) |
runtime/tests/ |
Node test suite (tsx --test) |
packages/pisper/ |
Private source manifest and npm installer/launcher published as pisper |
shared/ |
Small JS modules shared by runtime and client (e.g. workflow graph, release notes) |
src-tauri/ |
Tauri 2 shell (desktop bridge, pet window, updater, CLI install) |
src-tui/ |
Rust TUI (pisper CLI) |
scripts/ |
SEA packaging, release, smoke tests, i18n check |
docs/ |
Product docs, screenshots, sponsor config, packaging notes |
dist/ |
Vite production build output |
release/ |
Packaged SEA / TUI / Tauri artifacts (gitignored) |
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.
- today Changed · +10 lines · +329 tokens per session 921c500ee027
- 6d ago First seen · 165 lines · 3,780 tokens per session scan A aa666aff62ab
pisper AGENTS.md is an instructions file published in the GitHub repository ling-kong-ran/pisper (280 stars, last pushed today), licensed MIT. It adds 4,109 tokens to every session, about $0.0205 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 2026-08-30.
Other instructions, from other repositories
zashiki CLAUDE.md
Claude Code instructions for kounetsuman/zashiki, covering zashiki development conventions, comment conventions, testing, documentation (where design, specs, and context live) and issues vs. discussions.
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.
warp AGENTS.md
AGENTS.md instructions for warpdotdev/warp, covering agents.md, development commands, build and run, running with local warp-server and connect to server on default port 8080.
terax-ai AGENTS.md
AGENTS.md instructions for crynta/terax-ai, a project described as: Lightweight (7MB) Terminal-first AI-native dev workspace.
terminal-browser AGENTS.md
AGENTS.md instructions for zenbu-labs/terminal-browser, a project described as: A browser inside your terminal.
Better-Fullstack AGENTS.md
AGENTS.md instructions for Marve10s/Better-Fullstack, covering guidelines, web ui, workflow and bun.