DevVerse-SWE-Blog: Skill for Codex

.agents/skills/devverse-rag-chat/SKILL.md

devverse-rag-chat is a skill for Codex from hoangsonww/DevVerse-SWE-Blog. It costs 48 tokens per session (262 once invoked), scanned A, original, MIT.

A development guide for DevVerse's chat and retrieval system. Retrieval finds relevant article content, including from stored vectors and a local text-search fallback, while the chat response includes citations and source listings.

In plain words
What is it for?
Use it when changing the chat page, chat API, citation handling, article retrieval, or vectorisation pipeline. It covers Pinecone and Gemini integration, local fallback search, and validation of chat changes.
Why use it?
It keeps the backend and user interface using the same response and citation format. It also warns that stored search vectors can become outdated after article or chunking changes.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is hoangsonww/DevVerse-SWE-Blog's own configuration. It tells Codex how to work on DevVerse-SWE-Blog itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DevVerse-SWE-Blog configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hoangsonww/DevVerse-SWE-Blog. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hoangsonww/DevVerse-SWE-Blog/master/.agents/skills/devverse-rag-chat/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hoangsonww/DevVerse-SWE-Blog

Made for: Codex.

Wrote 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.

agentmods badge for devverse-rag-chat

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoangsonww/devverse-swe-blog/devverse-rag-chat.svg)](https://agentmods.dev/skills/hoangsonww/devverse-swe-blog/devverse-rag-chat)
Your own site
<a href="https://agentmods.dev/skills/hoangsonww/devverse-swe-blog/devverse-rag-chat"><img src="https://agentmods.dev/badge/skills/hoangsonww/devverse-swe-blog/devverse-rag-chat.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 262 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.00262
Opus 5 $0.00024 $0.00131
Sonnet 5 $0.00010 $0.00052
Haiku 4.5 $0.00005 $0.00026

Measured 3d ago against content hash 07eb73c541ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

devverse-rag-chat 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.

.agents/skills/devverse-rag-chat/SKILL.md · 24 lines

What it actually says

DevVerse RAG And Chat Workflow

  1. Preserve the response contract between backend and UI. The UI expects an answer string, a sources array, bracket citations in the answer body, and a trailing Sources: section that it strips before rendering.

  2. Keep citation parsing aligned with UI behavior. If you change citation formatting, update both lib/chat-citations.ts and the chat UI in the same task.

  3. Preserve hybrid retrieval unless you are intentionally redesigning it. lib/rag.ts merges Pinecone results with the local lexical fallback from lib/rag-local.ts.

  4. Read the detailed contract before changing retrieval, prompt format, or vector metadata. @references/rag-contract.md

  5. Assume Pinecone vectors are stale after article or chunking changes until vectorization is rerun.

  6. Validate chat changes with both tests and explicit runtime caveats. Use the devverse-validate skill for automated checks, then note any live env checks you could not perform.

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 3d ago First seen · 24 lines · 48 tokens per session scan A 07eb73c541ca

Subscribe to this mod's changes

devverse-rag-chat is a skill published in the GitHub repository hoangsonww/DevVerse-SWE-Blog (15 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 262 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

rag-knowledge

Work with the RAG knowledge base — ingest documents, run semantic search, manage collections, or add a sync source/connector (Google Drive, S3). Use when populating or debugging the knowledge base, tuning retrieval, or adding a new document source. This project uses {{ cookiecutter.vectorstore }} + {{…

vstorm-co/full-stack-ai-agent-template · 76 tokens

postgres-semantic-search

PostgreSQL-based semantic and hybrid search with pgvector and ParadeDB. Use when implementing vector search, semantic search, hybrid search, or full-text search in PostgreSQL. Covers pgvector indexing, hybrid FTS/BM25 + RRF, ParadeDB, reranking, halfvec, multilingual search, query translation, and domain evals.…

laguagu/claude-code-nextjs-skills · 228 tokens

Cursor rules for Next

Cursor rules for Next.js development with Tailwind CSS and TypeScript integration.

AmariahAK/atlarix-skills · 4 tokens

ask-ai

Configure the Ask AI (RAG-powered AI chat) in @farming-labs/docs. Use when enabling AI chat, setting mode (search vs floating), floatingStyle (panel, modal, popover, full-modal), position, providers, models, suggestedQuestions, apiKey, systemPrompt, or maxResults. Covers Next.js, SvelteKit, Astro, Nuxt and env vars.

farming-labs/docs · 83 tokens

oma-db

Database specialist for SQL, NoSQL, and vector database modeling, schema design, normalization, indexing, transactions, integrity, concurrency control, backup, capacity planning, data standards, anti-pattern review, and compliance-aware database design. Use for database, schema, ERD, table design, document model…

first-fluke/fullstack-starter · 111 tokens

searchrag-skill

A skill that sends a search query to a script and receives text from a retrieval-augmented generation system, which finds relevant source material before producing an answer.

kuc-arc-f/mcp_client_7ex · 37 tokens