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/xuzhougeng/wispterm/agents-mdgit clone --depth 1 https://github.com/xuzhougeng/wisptermWrote 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/xuzhougeng/wispterm/agents-md)<a href="https://agentmods.dev/instructions/xuzhougeng/wispterm/agents-md"><img src="https://agentmods.dev/badge/instructions/xuzhougeng/wispterm/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 | $0.05997 | $0.05997 |
| Opus 5 | $0.02998 | $0.02998 |
| Sonnet 5 | $0.01199 | $0.01199 |
| Haiku 4.5 | $0.00600 | $0.00600 |
Grade A, and why
wispterm 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Overview
WispTerm is a terminal emulator written in Zig, shipping desktop builds for Windows and macOS, plus an experimental Linux AppImage. It uses libghostty-vt (Ghostty's VT parser and terminal state machine) for terminal emulation, with its own rendering pipeline (D3D11/Metal/OpenGL + FreeType, plus DirectWrite/CoreText/fontconfig for font discovery by platform).
Windows is the primary and default development target (x86_64-windows-gnu), and day-to-day development happens on Windows in PowerShell. Platform-specific code lives behind narrow interfaces in src/platform/ (per-platform implementations plus _unsupported/_posix stubs) so macOS and Linux can share the terminal core. macOS is an active supported desktop build that is still stabilizing; Linux is experimental. See ROADMAP.md for future work and KNOWN_ISSUES.md for current platform limitations.
Architecture
WispTerm is split into a platform-agnostic core (terminal state, IO, rendering) and a per-platform host (window, event loop, input) that drives the core through a narrow surface API. The host interface is src/platform/window_backend.zig; OS facilities go through capability facades in src/platform/. The named contract — what the host implements, what services it supplies, and the invariants that keep the seam intact — is documented in docs/architecture.md. Read it before touching the platform boundary or starting a port.
UI presentation styles
WispTerm has exactly three application UI styles. Choose one before adding a screen; do not create a fourth ad-hoc overlay shape. The shared geometry contract is src/renderer/ui_patterns.zig. It is intentionally pure and is included in the fast test suite.
| Style | Use for | Required structure | Examples |
|---|---|---|---|
| Command palette | Find-and-run actions with no persistent form state | Search field, filtered and scrollable action list, visible selection, shortcut/meta column, Escape closes. Keep it transient; do not put multi-step configuration here. | Command Center, Copilot History picker |
| Form dialog | Small configuration, profile editing, confirmation, and launch choices | Centered constrained dialog, title plus one-line instruction, aligned rows/fields, explicit primary and cancel/close actions. Must fit inside viewport gutters at every size. | New Session, AI/SSH/MCP forms |
| Workbench page | Persistent tab-owned tools with browsing, status, or multi-column content | Header, content region, and a full-width footer/status band. Empty states explain why the page is empty and name the next action. Keyboard hints and non-blocking status belong in the footer/status band, never squeezed into a content column. | Settings, Memory Center, Skill Center, Port Forwarding, Agent History |
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.
- 4d ago First seen · 233 lines · 5,997 tokens per session scan A cff400c5b6b9
wispterm AGENTS.md is an instructions file published in the GitHub repository xuzhougeng/wispterm (399 stars, last pushed 6d ago), licensed MIT. It adds 5,997 tokens to every session, about $0.0300 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
liney AGENTS.md
AGENTS.md instructions for everettjf/liney, covering liney repository collaboration guide, 交流语言 / communication language, project overview, repository layout and build and test.
liney CLAUDE.md
Claude Code instructions for everettjf/liney, a project described as: Liney is a native macOS terminal workspace built with AppKit, SwiftUI, and Ghostty, designed for multi-repo workflows, worktree switching, and focused vibe coding.
orca AGENTS.md
AGENTS.md instructions for stablyai/orca, covering design system, electron ui validation, style, reuse before reimplementing and concise/brief non-obvious comments only.
outline-apps AGENTS.md
AGENTS.md instructions for OutlineFoundation/outline-apps, covering welcome to the outline monorepo!, repository structure, the npm run action command, common actions and other useful commands.
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.
outline-apps CLAUDE.md
Claude Code instructions for OutlineFoundation/outline-apps: This project uses AGENTS.md instead of CLAUDE.md.