suwappubot / api-ts
CLAUDE.md4 starsChanged 3 months agoApache-2.0View on GitHub
Scope: Hono routes (src/routes/), Effect-TS services, Drizzle ORM (src/db/schema/), A2A/MCP agent surface. - Tooling is bun only: bun run dev|build|check|test. Never bare tsc (hangs) or npm/npx. Type-check incrementally with bun run check. - Effect-TS discipline: services use Context.Tag + Layer + ManagedRuntime. Never mix raw Promises into Effect pipelines — wrap with Effect.tryPromise(). Env config comes from src/config/EnvService.ts (Effect Layer), not process.env reads. - CI checks OpenAPI and MCP schema drift — if you change a route or MCP tool,…
- Reads credentials
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- bot/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- showcase/CLAUDE.mdCLAUDE.md
- webapp/CLAUDE.mdCLAUDE.md
- gitbook/llms.txtllms.txt
- suwappubot-conventionsSkill
- aegis-goalSkill
- design-iterateSkill
- ethglobal-goalSkill
- evolveSkill
- goalSkill
- handoffSkill
- redesign-existing-projectsSkill
- reflectSkill
- suwappubot-conventionsSkill
- design-taste-frontendSkill
- suwappuSkill
The file
We split this CLAUDE.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: line 14
Drizzle schema changes: must mirror the Python runtime migration in database/db.py:_ensure_schema() (shared DB, ADR 0003).
≈ “Common” is an estimate: at least 1 in 5 of the 28,029 CLAUDE.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.
Files
api-ts/ — TypeScript API rules
Scope: Hono routes (src/routes/), Effect-TS services, Drizzle ORM
(src/db/schema/), A2A/MCP agent surface.
- Tooling is
bunonly:bun run dev|build|check|test. Never baretsc(hangs) ornpm/npx. Type-check incrementally withbun run check. - Effect-TS discipline: services use
Context.Tag+Layer+ManagedRuntime. Never mix raw Promises into Effect pipelines — wrap withEffect.tryPromise(). Env config comes fromsrc/config/EnvService.ts(Effect Layer), notprocess.envreads. - CI checks OpenAPI and MCP schema drift — if you change a route or MCP tool, regenerate the specs or CI fails.
- Drizzle schema changes must mirror the Python runtime migration in
database/db.py:_ensure_schema()(shared DB, ADR 0003). Followdocs/development/migrations.md. - Shared types live in
packages/sdk/src/types.ts(@suwappu/sdk) — changes ripple to webapp, mobile, and SDKs; check all three consumers. - New endpoints: copy an existing route file as the template. Agent-facing changes should keep
the agent card (
/.well-known/agent-card.json) and registry listings consistent —bash scripts/verify.sh agent. - This service is what
api.suwappu.botserves in prod.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

