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 instructions/willdady/platypus/claude-mdgit clone --depth 1 https://github.com/willdady/platypusWrote 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/instructions/willdady/platypus/claude-md)<a href="https://agentmods.dev/instructions/willdady/platypus/claude-md"><img src="https://agentmods.dev/badge/instructions/willdady/platypus/claude-md.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 | $0.01428 | $0.01428 |
| Opus 5 | $0.00714 | $0.00714 |
| Sonnet 5 | $0.00286 | $0.00286 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
platypus CLAUDE.md 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Overview
Platypus is a full-stack app for building and managing AI agents with tool support and multi-provider capabilities. pnpm workspaces + Turborepo monorepo.
Setup & Commands
pnpm install
cp apps/frontend/.env.example apps/frontend/.env
cp apps/backend/.env.example apps/backend/.env
pnpm dev # frontend + backend + local Postgres
pnpm drizzle-kit-push # apply schema changes (requires `pnpm dev` running)
pnpm build
pnpm format
pnpm lint
pnpm typecheck # tsc --noEmit (apps/backend, apps/frontend); gated in CI
pnpm test # all tests (Vitest, orchestrated by Turborepo)
Per-package: pnpm --filter <pkg> test|test:watch|test:coverage|typecheck.
pnpm typecheck runs tsc --noEmit for every package exposing a typecheck
script, test files included. CI fails on any type error — ESLint does not catch
them, so run it before pushing. Other packages join the gate by adding their own
typecheck script.
Default admin on first startup: [email protected] / admin123 (override via ADMIN_EMAIL / ADMIN_PASSWORD).
Monorepo Layout
apps/backend— Hono.js REST API, Drizzle ORM (Postgres 17), better-auth at/auth/*. Schema insrc/db/, routes insrc/routes/, run lifecycle insrc/runs/. Entry:apps/backend/index.ts.apps/frontend— Next.js 16 App Router. Multi-tenant routes underapp/[orgId]/workspace/[workspaceId]/.... Tailwind v4 + Radix.packages/schemas— Shared Zod schemas (@platypus/schemas). Each domain model has full / create / update variants.
Domain hierarchy: Organization → Workspace → Chat / Agent / MCP / Provider.
Known Constraints
drizzle-kit pushapplies DDL only — it does NOT run migration.sqlfiles. Data migrations (e.g. custom backfills) run in production viascripts/migrate.ts(drizzle-kit migrate) but are skipped by the dev push flow. In dev, apply any needed data changes manually (e.g. attach org-scoped Shared resources via the UI).- Postgres 18 is not supported (Drizzle ORM incompatibility).
- No TypeScript parameter properties. Node's strip-only TS mode rejects
constructor(private x: T)shorthand. Declare fields explicitly and assign in the constructor body. - Format with Prettier conventions.
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.
- 3d ago First seen · 116 lines · 1,428 tokens per session scan A aa5272b49c40
platypus CLAUDE.md is an instructions file published in the GitHub repository willdady/platypus (71 stars, last pushed today), licensed MIT. It adds 1,428 tokens to every session, about $0.0071 per session on Opus 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 2026-09-01.
Other instructions, from other repositories
sciclaw AGENTS.md
AGENTS.md instructions for drpedapati/sciclaw: For end-to-end implementation and pull-request work, use the vendored repository skill at .agents/skills/ship-job/SKILL.md. Read it completely before changing files, and use .agents/skills/ship-job/references/sciclaw-release.md for any separately authorized merge…
waku-agent CLAUDE.md
Instructions for ShenSeanChen/waku-agent, covering waku-agent — working conventions, architecture map (file ↔ diagram box), rules and commands.
commonly CLAUDE.md
Claude Code instructions for Team-Commonly/commonly, covering claude.md / agents.md, 🧠 product vision & architecture philosophy, what commonly is, the architecture model and key concepts.
Assistant CLAUDE.md
Claude Code instructions for bearlike/Assistant, covering agents guide — mewbo, mandatory: hydrate before touching files, what mewbo is, monorepo layering — read before adding a module and engineering principles.
coach AGENTS.md
AGENTS.md instructions for watt-mind/coach, covering agent guidelines (agents.md), project, issue tracking, non-negotiables for agents and execution loop.
recurgent AGENTS.md
Instructions for kulesh/recurgent, covering agents.md, first things first, issue tracking, assistant's role and philosophy.