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/kingsword09/ptywright/agents-mdgit clone --depth 1 https://github.com/kingsword09/ptywrightWrote this? Show the measurements
A badge for your README with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them.
[](https://agentmods.dev/instructions/kingsword09/ptywright/agents-md)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 | $0.01254 | $0.01254 |
| Opus 5 | $0.00627 | $0.00627 |
| Sonnet 5 | $0.00251 | $0.00251 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
ptywright 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 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.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ptywright - Agent Notes
Project Goal
Build and maintain a universal terminal/TUI observability and regression driver:
launch commands through a PTY, feed ANSI/VT output into @xterm/headless,
rebuild terminal state, and expose that state through MCP tools, scripts,
cassettes, and browser-terminal regression workflows.
Priorities:
- Deterministic regression first: stable snapshots, masks, explicit waits, goldens, and replayable artifacts.
- Agent visibility second: let agents inspect terminal semantics before relying on visual screenshots.
- Portable artifacts: generated summaries/manifests must remain useful after copied or moved.
Design Principles
- KISS: keep the smallest reliable loop for each workflow.
- YAGNI: avoid pixel diff, terminal component-tree inference, or app-specific contracts unless a milestone needs them.
- DRY: snapshot/wait/normalize logic belongs in
src/terminal/,src/session/,src/script/, andsrc/agent/, not scattered across tests. - SOLID: keep PTY adapters, session lifecycle, rendering, MCP tools, script runner, and browser-agent runner separated by clear contracts.
Quick Start
- Install dependencies:
bun install - Local CLI help:
bun run src/cli.ts help - Start MCP server:
bun run src/cli.ts mcp - Run unit/regression tests:
bun run test - Run committed agent cassette check:
bun run agent:check - Full gate:
bun run check - Lint:
bun run lint - Format:
bun run format/bun run format:check
Documentation Map
README.md/README_ZH.md: concise product entry points.docs/mcp.md: live terminal MCP usage.docs/script-runner.md: JSON/TS script runner and goldens.docs/pty-cassette.md: raw PTY record/replay and wrapper APIs.docs/agent-regression.md: browser terminal flows, replay, promote, check.docs/browser-terminal-harness.md: downstream browser renderer harness pattern for raw PTY cassette replay.docs/artifacts-and-ci.md: failure triage, manifests, reusable commands, CI.docs/documentation-maintenance.md: docs/schema/CLI/example sync checklist.plan.md: roadmap, milestones, decision log.DEEPRESEARCH.md: historical research status and current implementation decision, not active architecture instructions.
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 · 120 lines · 1,254 tokens per session scan A 2aee1986c80e
ptywright AGENTS.md is an instructions file published in the GitHub repository kingsword09/ptywright (1 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,254 tokens to every session, about $0.0063 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.
Other instructions, from other repositories
terminal AGENTS.md
Instructions for browser-use/terminal, covering agent notes, rust rewrite verification loop and terminal ui testing standard.
hex1b AGENTS.md
Instructions for mitchdenny/hex1b, covering ai coding agent guidelines for hex1b, 🛠️ available skills, 📋 project overview, key technologies and repository layout.
unifly AGENTS.md
Instructions for hyperb1iss/unifly, covering agents.md, what this repository is, quick command reference, the canonical "before commit" gate and individual gates.
waveloom AGENTS.md
Instructions for Menfre01/waveloom, covering waveloom, 项目概要, 编码规范, 代码审查 and 开发流程.
lazyazure AGENTS.md
AGENTS.md instructions for matsest/lazyazure, covering lazyazure - agent guidelines, project overview, critical guidelines, 1. tui development with gocui and 2. mutex best practices.
r3bl-open-core AGENTS.md
Instructions for r3bl-org/r3bl-open-core, covering agent instructions for r3bl-open-core, ai agent security & system integrity mandates, 1. critical directory protection, 2. ownership & integrity and 3. execution safety.