Borrowing it
Nothing to install: this file belongs to duc01226/EasyPlatform. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/duc01226/EasyPlatform/main/CLAUDE.mdgit clone --depth 1 https://github.com/duc01226/EasyPlatformWrote 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/duc01226/easyplatform/claude-md)<a href="https://agentmods.dev/instructions/duc01226/easyplatform/claude-md"><img src="https://agentmods.dev/badge/instructions/duc01226/easyplatform/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 5.1 | $0.15306 | $0.15306 |
| Opus 5 | $0.07653 | $0.07653 |
| Sonnet 5 | $0.03061 | $0.03061 |
| Haiku 4.5 | $0.01531 | $0.01531 |
Grade A, and why
EasyPlatform 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 — 600 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[WORKFLOW-GATE] — routing is your FIRST action, before any tool call. This rule is hook-independent: it binds Claude and Codex equally. Do not wait for any injected reminder to apply it.
Classify complexity and risk first, then route it:
Request is about… Default route A simple, straightforward task with a clear target and low risk direct execution — do it without a workflow A simple task that needs a few coordinated steps or skills custom simple workflow — sequence only the necessary skills/steps A non-trivial bug, error, crash, regression, or wrong/stale output workflow-bugfixworkflow —/start-workflow workflow-bugfixA non-trivial new feature, capability, or enhancement workflow-featureworkflow —/start-workflow workflow-feature(useworkflow-big-featurewhen scope is large, ambiguous, or research-heavy)Anything matching a skill's or workflow's "Use" clause that skill / workflow A one-off question, or a truly trivial edit direct execution
- An explicit
/skillor/workflowin the prompt is the user's choice — execute it directly. Otherwise auto-select the route yourself; never ask the user which path to take.- Analyze whether the task is simple and straightforward before defaulting to a standard workflow. If the target is clear, the change is low-risk, and a short direct execution can satisfy it, choose direct execution.
- For simple but multi-step work, build a custom simple workflow with only the few relevant skills/steps. Do not expand to a full standard workflow when a small custom sequence is enough.
- Use standard workflows for non-trivial bugs and feature/enhancement work — they force the investigation, tests, and review that risky or broad changes need.
- Declare the route, then ACTIVATE it — declaring is not activating. State
Route: {workflow-id | skill | custom-simple | direct} — because {reason}, then:
- Workflow route → invoke
/start-workflow <id>as a tool call. That skill loads the workflow's canonical stepsequenceand creates the task list 1:1 from it. You MUST NOT hand-author your own task list for a workflow route — the canonicalsequenceis the only source of truth. WritingRoute: …in prose and then improvising a few tasks is the failure this gate exists to prevent.- Skill route → invoke that skill via the
Skilltool.- Custom simple workflow → create a small task list from the selected skills/steps, then execute them in order.
- Direct route → build the task list yourself, then proceed. In every case the route must be activated BEFORE the first edit, sub-agent, or command.
- Direct execution is a legitimate route for trivial, one-off, or simple straightforward work — but the declare-route and activate steps still apply.
- Scaffolding-first for new foundations.
workflow-greenfield-initandworkflow-big-featurescaffold a REVIEWED (architecture-review-full), example-rich, convention-bearing foundation — base abstractions + golden-path example code + a project-reference doc set — BEFORE fanning out feature work; features never build on an unreviewed foundation.
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 · 600 lines · 15,306 tokens per session scan A 46ba01d59cdb
EasyPlatform CLAUDE.md is an instructions file published in the GitHub repository duc01226/EasyPlatform (9 stars, last pushed 17d ago), licensed MIT. It adds 15,306 tokens to every session, about $0.0765 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 2026-09-03.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.