Instructor is a library that helps applications obtain structured, validated data from language models using Pydantic models. It is for developers building LLM features such as data extraction across different model providers, and the catalogue entries add usage rules and instructions.
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.
git clone --depth 1 https://github.com/567-labs/instructorWrote 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/rules/567-labs/instructor/new-features-planning)<a href="https://agentmods.dev/rules/567-labs/instructor/new-features-planning"><img src="https://agentmods.dev/badge/rules/567-labs/instructor/new-features-planning/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/567-labs/instructor/new-features-planning"><img src="https://agentmods.dev/badge/rules/567-labs/instructor/new-features-planning.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00488 | $0.00488 |
| Opus 5.5 | $0.00195 | $0.00195 |
| Sonnet 5.5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
new-features-planning scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
- When being asked to make new features, make sure that you check out from main a new branch and make incremental commits
- Use conventional commit format:
<type>(<scope>): <description>- Types: feat, fix, docs, style, refactor, perf, test, chore
- Example:
feat(validation): add email validation function - Keep commits focused on a single change
- Write descriptive commit messages in imperative mood
- Use
git commit -m "type(scope): subject" -m "body" -m "footer"for multiline commits
- Use conventional commit format:
- If the feature is very large, create a temporary
todo.md - And start a pull request using
gh- Create PRs with multiline bodies using:
gh pr create --title "feat(component): add new feature" --body "$(cat <<EOF ## Description Detailed explanation of the changes ## Changes - List important changes - Another change ## Testing How this was tested This PR was written by [Cursor](cursor.com) EOF )" -r jxnl,ivanleomk - Or use the
-Fflag with a file:gh pr create -F pr_body.md
- Create PRs with multiline bodies using:
- Make sure to include
This PR was written by [Cursor](mdc:cursor.com) - Add default reviewers:
- Use
gh pr edit <id> --add-reviewer jxnl,ivanleomk - Or include
-r jxnl,ivanleomkwhen creating the PR
- Use
- use
gh pr view <id> --comments | catto view all the comments - For PR updates:
- Do not directly commit to an existing PR branch
- Instead, create a new PR that builds on top of the original PR's branch
- This creates a "stacked PR" pattern where:
- The original PR (base) contains the initial changes
- The new PR (stack) contains only the review-related updates
- Once the base PR is merged, the stack can be rebased onto main
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.
- 1mo ago First seen · 46 lines · 488 tokens per session scan A a71203e7cc37
new-features-planning is a cursor rule published in the GitHub repository 567-labs/instructor (14,032 stars, last pushed 4d ago), licensed MIT. It adds 488 tokens to every session, about $0.0020 per session on Opus 5.5. 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 2026-08-30.
Other cursor rules, from other repositories
backend-rules
A set of rules for developing backend services with FastAPI, a Python framework for building web APIs.
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
python
Python best practices and patterns for modern software development with Flask and SQLite.
django
Definitive guidelines for writing maintainable, performant, and secure Django applications, emphasizing modern best practices, clear code organization, and efficient patterns.
rich
Definitive guidelines for building robust, maintainable, and visually appealing Python CLI applications using the rich library.
developer-advocate
Expert developer advocate specializing in building developer communities, creating compelling technical content, optimizing developer experience (DX), and driving platform adoption through authentic engineering engagement. Bridges product and engineering teams with external developers.