Borrowing it
Nothing to install: this file belongs to enwong93-sketch/devspace-ultra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/enwong93-sketch/devspace-ultra/main/AGENTS.mdgit clone --depth 1 https://github.com/enwong93-sketch/devspace-ultraWrote 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/enwong93-sketch/devspace-ultra/agents-md)<a href="https://agentmods.dev/instructions/enwong93-sketch/devspace-ultra/agents-md"><img src="https://agentmods.dev/badge/instructions/enwong93-sketch/devspace-ultra/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/enwong93-sketch/devspace-ultra/agents-md"><img src="https://agentmods.dev/badge/instructions/enwong93-sketch/devspace-ultra/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01570 | $0.01570 |
| Opus 5 | $0.00785 | $0.00785 |
| Sonnet 5 | $0.00314 | $0.00314 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade A, and why
devspace-ultra 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevSpace Ultra Agent Notes
Execution approval
When the user explicitly asks this DevSpace Ultra plugin session to investigate, research, diagnose, audit, inspect, or run a non-destructive read-only probe, treat that request itself as approval to begin immediately. Do not insert a separate “continue?”, “start?”, or design-approval checkpoint before gathering evidence.
Only add a new confirmation when a later step crosses into a materially different destructive, production-mutating, service-stopping, credential-changing, publishing, or otherwise higher-risk action that was not already authorized by the user.
Interactive ChatGPT progress routing
Every user-facing ChatGPT Classic Main conversation uses one conversation-scoped floating DevSpace progress narration card. Never rely on, create, or remount the retired inline black Goal Dock or inline Plan Card as the progress surface.
Before the first substantive work tool in any task expected to require more than one tool call, more than roughly 30 seconds, or multiple verification gates, start or resume exactly one conversation-bound DevSpace Plan. When the requested outcome needs autonomous continuation across assistant turns, start or resume Goal Mode first and keep a fresh turn-scoped Plan beneath it. Keep Goal and Plan state current as execution structure and backend telemetry; neither tool events nor timers may author visible narration.
Visible progress is authored only by the working Agent. Call devspace_progress_report when a meaningful medium-sized step has completed, an important verification result is available, the execution direction materially changes, or a genuine blocker is useful to report. There is no fixed time or tool-count cadence, and low-level tool events, timers, heartbeat rows, step counters, and generic status boilerplate must never be shown as narration. Write the update yourself in natural language for this user and current task. The report binds to the current authoritative conversation and waits for identity correlation instead of failing on a short wall-clock deadline. Do not expose hidden reasoning, and do not create synthetic user turns, reloads, or navigation merely to update progress. A genuinely atomic one-tool task may leave the blank conversation card untouched.
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 · +286 tokens per session eabb44e64abf
- 2d ago First seen · 32 lines · 1,284 tokens per session scan A db62aed3f481
devspace-ultra AGENTS.md is an instructions file published in the GitHub repository enwong93-sketch/devspace-ultra (46 stars, last pushed 2d ago), licensed MIT. It adds 1,570 tokens to every session, about $0.0078 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 2026-09-10.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).