Agent Guide - #474
Open
ChengShi-1 wants to merge 4 commits into
Open
Conversation
pdurbin
reviewed
Aug 4, 2026
Contributor
There was a problem hiding this comment.
Pull request overview
Adds a new repository-root AGENTS.md meant to serve as the canonical “agent guide” for AI tools and contributors working in this SDK repo, documenting architecture, HTTP/auth behavior, and testing/CI workflows.
Changes:
- Introduces
AGENTS.mddescribing the SDK’s clean-architecture layering and composition-root pattern. - Documents HTTP/auth configuration patterns and common “gotchas”.
- Documents test suite structure (unit/integration/functional) and CI workflow expectations.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What this PR does / why we need it:
Adds an
AGENTS.mdat the repo root.Claude generated the initial draft as a skill, but this markdown is not one skill here.
AGENTS.mdis read as always-on context for the whole repo, while a skill only loads when its description matches the current task.Claude said "Broad "here's our whole architecture" content is exactly the kind of thing you want always-on — converting it to a skill risks it getting silently skipped on tasks that don't obviously match the trigger phrase. Skills fit better for narrower, task-shaped guidance (e.g. "how to test against a different js-dataverse PR build" is more skill-shaped than "our layering conventions").
Optionally, splitting
AGENTS.mdinto some small skills (e.g. writing new use case, testing troubleshooting) would be good to shrink the markdown to the core architecture content."I added notes and questions based on problems I encountered while working with it, including how to handle flaky tests and how to verify API behavior before writing new use cases.
Additional guidance is welcome, especially rules that could reduce hallucinations and improve the agent’s accuracy and overall performance.
A human readable format, link for
AGENTS.md: https://github.com/IQSS/dataverse-client-javascript/blob/d90e9b009849a7c8f88543e5ef3905571d55cc1f/AGENTS.mdWhich issue(s) this PR closes:
Related Dataverse PRs:
Special notes for your reviewer:
GitHub Copilot can read for every chat and PR-review interaction in this repo by design; that's the entire reason that file exists.
Tools that natively support the
AGENTS.mdconvention (Cursor, Codex, and others converging on it) load it as ambient context automatically too. Zero prompt needed. Codex or Copilot auto-discoversAGENTS.mdat the repo root and loads it as instructions for every session in that repo.Suggestions on how to test this:
No functional code changed; this is documentation only.
Is there a release notes or changelog update needed for this change?:
No. This only adds contributor/agent documentation; it doesn't change any use case, public API, or behavior.
Additional documentation:
AGENTS.md