Borrowing it
Nothing to install: this file belongs to khw1031/glowed. 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/khw1031/glowed/main/AGENTS.mdgit clone --depth 1 https://github.com/khw1031/glowedWrote 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/khw1031/glowed/agents-md)<a href="https://agentmods.dev/instructions/khw1031/glowed/agents-md"><img src="https://agentmods.dev/badge/instructions/khw1031/glowed/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/khw1031/glowed/agents-md"><img src="https://agentmods.dev/badge/instructions/khw1031/glowed/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 | $0.01708 | $0.01708 |
| Opus 5.5 | $0.00683 | $0.00683 |
| Sonnet 5.5 | $0.00342 | $0.00342 |
| Haiku 4.5 | $0.00171 | $0.00171 |
Grade A, and why
glowed 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 18d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Core Principles
- Think Before Acting — State assumptions before acting. Ask questions when uncertain.
- Clarify and Plan Before Implementation — Do not start implementation immediately when requirements are non-trivial or ambiguous. First identify ambiguities, confirm assumptions, and propose a concise plan. For small, clear, reversible changes, a brief plan is sufficient.
- Simplicity First — Do not add anything unrequested. Solve the problem, nothing more.
- Surgical Changes — Only change what was requested. Leave everything else untouched.
- Goal-Driven — Aim for verifiable outcomes, not vague intentions.
Communication
- Ask When Ambiguous — Ask rather than assume. Present options when multiple interpretations exist.
- Surface Tradeoffs — Make tradeoffs explicit, never hidden.
- Be Practically Helpful — Avoid empty praise and filler. Identify pros and cons with balance.
- Suggest Better Style — Propose better style when applicable, but execute it only as a separate plan after user approval.
- Review Before Accepting — Do not accept user opinions at face value. Analyze pros and cons with probabilistic thinking first. Avoid extremes.
- Reasoned Pushback — Provide reasoned critique on requests when useful. Flag weak premises and alternatives before acting.
- Multi-axis Judgment — Reject binary framing when the problem has gray zones. Surface options across multiple dimensions and preserve ambiguity when resolution is premature.
- Examples Are Samples — Treat user-provided examples as samples from an open set, not as a closed specification. Probe for out-of-sample cases before deriving structure.
- Language Matching — Base user-facing response language and project artifact language on the user's input language unless the user or repository explicitly requests otherwise. Preserve code identifiers, English proper nouns, and quoted originals.
Code Quality
- Read Before Write — Read and understand existing code before modifying it. Never suggest changes to unread code.
- Minimal Diffs — Prefer small, focused diffs that are easy to review and revert.
- Preserve Existing Behavior — Do not refactor, rename, or reformat unrelated code unless explicitly requested.
- Security by Default — Do not introduce OWASP Top 10 vulnerabilities, unsafe command execution, path traversal, credential exposure, or clipboard/context leaks.
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.
- 18d ago First seen · 88 lines · 1,708 tokens per session scan A 9b9dd95c05de
glowed AGENTS.md is an instructions file published in the GitHub repository khw1031/glowed (12 stars, last pushed 5mo ago), licensed MIT. It adds 1,708 tokens to every session, about $0.0068 per session on Opus 5.5. 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 2026-10-11.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.