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.
curl -O https://raw.githubusercontent.com/hoangsonww/DevVerse-SWE-Blog/master/.agents/skills/devverse-refresh-vectors/SKILL.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/skills/hoangsonww/devverse-swe-blog/devverse-refresh-vectors)<a href="https://agentmods.dev/skills/hoangsonww/devverse-swe-blog/devverse-refresh-vectors"><img src="https://agentmods.dev/badge/skills/hoangsonww/devverse-swe-blog/devverse-refresh-vectors.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 5.1 | $0.00043 | $0.00191 |
| Opus 5 | $0.00022 | $0.00096 |
| Sonnet 5 | $0.00009 | $0.00038 |
| Haiku 4.5 | $0.00004 | $0.00019 |
Grade A, and why
devverse-refresh-vectors 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 2d 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.
What it actually says
DevVerse Vector Refresh Workflow
-
Confirm why the refresh is needed. Common triggers are article content changes, metadata changes, chunking changes, or Pinecone metadata changes.
-
Read the vectorization notes before running anything. @references/vectorization-notes.md
-
Check for required env variable names without reading their values. Use
.env.exampleas the contract. -
Explain that vector refresh calls external services. The script uses Gemini embeddings and Pinecone upserts.
-
Run
npm run vectorize:articlesonly when the user explicitly wants the refresh or the task clearly requires it. -
Report what changed, whether the refresh ran, and any env or quota blockers.
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.
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.
- 2d ago First seen · 23 lines · 43 tokens per session scan A 9b5d4ec9fce4
devverse-refresh-vectors is a skill published in the GitHub repository hoangsonww/DevVerse-SWE-Blog (15 stars, last pushed 21d ago), licensed MIT. It adds 43 tokens to every session and 191 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.
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 }} + {{…
pr-review
AI-assisted review of one or more GitHub Pull Requests. Offloads deterministic checks (lint, complexity, duplication, security, perf) to repo linters via self-contained scripts, then applies LLM judgment to what linters cannot catch and posts high-signal findings after a single human approval. Pass one or many PRs…
pr-address-comments
Read a remote GitHub PR's review comments, implement fixes on the PR branch, then reply to and resolve addressed threads (REST reply + GraphQL resolveReviewThread). Use for /pr-address-comments, a single PR URL or number, when not using the parallel batch skill pr-address-comments-all. Requires gh and a git checkout…
essentials-sync
Extract a jargon-free ess- shared package out of a team- or account-specific tool in a private repo and sync it to the open-source essentials repo, with deterministic scanners and an adversarial LLM reviewer in between. Use when the user runs /essentials-sync, asks to open-source a package, extract an ess- package…
summarize-change-log
Condense long commit logs, squash messages, or change narratives into 1–5 GitHub-ready markdown bullets with Conventional Commit subjects (≤50 chars). Use when the user asks to summarize a git log, boil down commits, write a squash-merge message, or produce a five-bullet PR/merge summary.
knowledge-search
Answer questions from the organization's indexed documents using knowledgesearch, and cite every claim back to a retrieved passage. Use whenever a question is about document content. Covers the search-first rule, answering only from the closed set of returned passages, the Sources list format, and how to tell an empty…