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/hoangsonww/devverse-swe-blog/agents-mdgit clone --depth 1 https://github.com/hoangsonww/DevVerse-SWE-BlogWrote 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/hoangsonww/devverse-swe-blog/agents-md)<a href="https://agentmods.dev/instructions/hoangsonww/devverse-swe-blog/agents-md"><img src="https://agentmods.dev/badge/instructions/hoangsonww/devverse-swe-blog/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 | $0.00750 | $0.00750 |
| Opus 5 | $0.00375 | $0.00375 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
DevVerse-SWE-Blog 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevVerse Codex Guidance
Core Expectations
- Treat
content/*.mdxas the canonical article store. The SQL article schemas insupabase/are not the runtime source of article content. - Prefer code over README when they conflict. Parts of the README are stale.
- Keep changes narrow. This repo has duplicated article parsers and several UI/data contracts that are easy to break with broad refactors.
- Do not read or print real secret values from
.envor.env.*. Use.env.examplefor variable names and expected configuration. - Use
rgandrg --filesfor search.
Architecture Invariants
- Preserve the split between
/and/home. /is the landing page and intentionally hides the navbar./homeis the article browser.- Preserve
.mdx-containerand theh2/h3article heading structure.components/TableOfContents.tsxdepends on both. - Preserve the dark-mode chain across:
- the inline boot script in
app/layout.tsx - the
darkclass on<html> - CSS variables in
app/globals.css provider/DarkModeProvider.tsx
- the inline boot script in
- Preserve the chat response contract across
app/chat/page.tsx,lib/chat-citations.ts, andlib/rag.ts.- assistant answers use bracket citations
- backend appends a trailing
Sources:section - UI strips that section and links citations to
message.sources
MDX Content Contract
- Keep article metadata as a literal
export const metadata = { ... };. - Keep
title,description, andtopicsas literal string/array fields. - Keep
### Author: .... - Keep
> Date: YYYY-MM-DD. - Keep article body starting with a top-level
#heading. - If you change that contract, update all dependent parsers together:
lib/rss.tslib/rag-local.tsscripts/vectorize_articles.mjs- any affected tests
Security Boundaries
- Keep
SUPABASE_SERVICE_ROLE_KEYserver-only. - Treat these routes as security-sensitive:
app/api/verify-email/route.tsapp/api/reset-password/route.ts
- Do not move service-role Supabase code into shared modules imported by client code.
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 First seen · 71 lines · 750 tokens per session scan A 3a8b078c6f3e
DevVerse-SWE-Blog AGENTS.md is an instructions file published in the GitHub repository hoangsonww/DevVerse-SWE-Blog (15 stars, last pushed 19d ago), licensed MIT. It adds 750 tokens to every session, about $0.0037 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 2026-09-04.
Other instructions, from other repositories
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
appwrite CLAUDE.md
Claude Code instructions for appwrite/appwrite, a project described as: Appwrite® - complete cloud infrastructure for your web, mobile and AI apps. Including Auth, Databases, Storage, Functions, Messaging, Hosting, Realtime and more.
nodejs-starter CLAUDE.md
Claude Code instructions for threeal/nodejs-starter, covering claude.md, about this repository, architecture, source files and build outputs.
exeslim AGENTS.md
AGENTS.md instructions for ryanlewis/exeslim, a project described as: Minimal exe.dev base image for deployment targets — systemd and full platform wiring, without the agent workstation toolchain.
linux AGENTS.md
AGENTS.md instructions for sxxpqp/linux, covering linux ops notes — ai 协作上下文, 仓库性质(重要), 详细参考(按需加载,不默认占 context), 共享基础设施 — 核心入口(每次都要用) and 子目录优先级 / 当前活跃区域.
linux CLAUDE.md
Claude Code instructions for sxxpqp/linux, covering linux ops notes — ai 协作上下文, 仓库性质(重要), 详细参考(按需加载,不默认占 context), 共享基础设施 — 核心入口(每次都要用) and 子目录优先级 / 当前活跃区域.