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 agents/antgroup/vsag/contribution-workflowgit clone --depth 1 https://github.com/antgroup/vsagWrote 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/agents/antgroup/vsag/contribution-workflow)<a href="https://agentmods.dev/agents/antgroup/vsag/contribution-workflow"><img src="https://agentmods.dev/badge/agents/antgroup/vsag/contribution-workflow.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 | $0.00000 | $0.01406 |
| Opus 5 | $0.00000 | $0.00703 |
| Sonnet 5 | $0.00000 | $0.00281 |
| Haiku 4.5 | $0.00000 | $0.00141 |
Grade A, and why
contribution-workflow 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contribution Workflow
Branching
- Before modifying code, create and switch to a working branch from an
up-to-date
main. - When preparing a pull request, inspect the configured remotes and prefer the
contributor's fork as the push target. Treat
antgroup/vsagas the upstream repository, not the default destination for working branches. - Push a working branch directly to
antgroup/vsagonly when the task explicitly requires it or the contributor has authorized it. - Keep changes scoped and reviewable.
Commit messages
- Follow Conventional Commits:
feat:,fix:,docs:,chore:,refactor:, etc. - Commits in this project are expected to carry a DCO
Signed-off-by:trailer. - Only humans can legally certify the DCO; AI coding agents must not add
their own
Signed-off-bytrailer. The human submitter is responsible for reviewing AI-generated changes, ensuring license compliance, and taking full responsibility for the contribution. - AI agents must NOT invoke
git commit -s.-sappends aSigned-off-by:trailer at the very end of the message and inserts a blank line before it if other trailers are present, which separates the human sign-off from theAssisted-by:line and reverses the required order. Instead, write both trailers directly in the commit message body. Derive the human identity from the active git configuration (git config user.nameandgit config user.email) and format it asSigned-off-by: <Name> <email>. - For changes produced with AI assistance, attribute the agent with an
Assisted-by:trailer in the formAssisted-by: AgentName:ModelVersion(see the Linux kernel AI Coding Assistants policy). DetermineAgentNameandModelVersionat execution time from the active agent name and model name (for exampleAssisted-by: OpenCode:claude-opus-4.7). - Trailer order and spacing: a single blank line separates the subject
(and optional body) from the trailer block. Inside the trailer block,
place the human
Signed-off-by:first and theAssisted-by:line immediately after, with no blank line between them. Example:
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 · 121 lines · 0 tokens per session scan A 487a98884a03
contribution-workflow is an agent published in the GitHub repository antgroup/vsag (507 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,406 tokens. 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 2026-09-03.
Other agents, from other repositories
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
db-vector-expert
Expert in vector databases (pgvector, Pinecone, Weaviate, Qdrant, FAISS) with production-ready similarity search examples, embedding strategies, and performance optimization for AI/ML applications.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.