razorpayrazorpay/blade/AGENTS.md

blade

AGENTS.md658 starsChanged 4 months agoMITView on GitHub

This is the monorepo for the Blade Design System. It contains different packages related to the Blade Design System of Razorpay. Load the Agents Context File in your context whenever change is being made to that particular package. Use CLAUDE.md when you are using Claude Code and AGENTS.md when you are using Cursor or other coding tool. .. And few other smaller packages related to blade We want to know if the intent of the user is to build complete…

We split this AGENTS.md into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
When intent is perform-task-end-to-end, load perform-task-end-to-end skill in your context and do the task end-to-end as guided by the …
line 32

≈ “Common” is an estimate: at least 1 in 5 of the 36,368 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

AGENTS.md

Blade Monorepo — Agent Context

This is the monorepo for the Blade Design System. It contains different packages related to the Blade Design System of Razorpay.

Packages

Load the Agents Context File in your context whenever change is being made to that particular package. Use CLAUDE.md when you are using Claude Code and AGENTS.md when you are using Cursor or other coding tool.

Package	Agents Context File	Description
blade	./packages/blade/CLAUDE.md or AGENTS.md	The core Blade Design System package with cross-platform UI components for React Web and React Native
blade-plugin	./packages/blade-plugin/CLAUDE.md or AGENTS.md	Claude Code plugin + cross-agent skills. Owns the Blade knowledgebases for React and Svelte (component/pattern/general docs for AI agents)
blade-mcp	./packages/blade-mcp/CLAUDE.md or AGENTS.md	Model Context Protocol (MCP) server for AI-assisted development using Blade components (maintenance mode)
blade-core	./packages/blade-core/CLAUDE.md or AGENTS.md	Core utilities for Blade Design System (Only used in blade-svelte as of now and not in blade package)
blade-svelte	./packages/blade-svelte/CLAUDE.md or AGENTS.md	Svelte components for Blade Design System (changes here should only be made when explicitly asked by the user for svelte changes)

.. And few other smaller packages related to blade

Finding Task Intent

We want to know if the intent of the user is to build complete feature/fix end-to-end (in that case we would want to write tests, fix lints, fix snapshots, etc) or its a small casual prompt to iterate over task faster where scope of task is limited to what user has asked for.

# existence of GITHUB__RZP_SWE_AGENT_APP__APP_ID environment variable in the session, implies that this request was triggered on cloud agent where the intent is to build things end-to-end.
if [ -z "$GITHUB__RZP_SWE_AGENT_APP__APP_ID" ]; then
  echo "Intent: 'normal-task'"
else
  echo "Intent: 'perform-task-end-to-end'"
fi

When intent is perform-task-end-to-end, load perform-task-end-to-end skill in your context and do the task end-to-end as guided by the skill.

Download now (ZIP)

Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 28,693 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository19 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/agent-base-directory.mdcCursor rule
- .cursor/rules/orchestrator-guardrails.mdcCursor rule
- .cursor/rules/svelte-migration.mdcCursor rule
- check-component-readinessSkill
- code-reviewSkill
- create-prSkill
- get-agentic-blade-metricsSkill
- heal-prSkill
- migrate-to-rnSkill
- migrate-to-svelteSkill
- perform-task-end-to-endSkill
- resolve-commentsSkill
- review-prSkill
- update-componentSkill
- verify-with-browserSkill
- write-api-decisionSkill
- write-biweekly-announcementSkill
- write-unit-testsSkill

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free