indonesia-civic-stack: Instructions file for Claude Code

CLAUDE.md

indonesia-civic-stack CLAUDE.md is an instructions file for Claude Code from suryast/indonesia-civic-stack. It costs 475 tokens per session, scanned A, original, MIT.

Repository instructions for a Python SDK that provides access to Indonesian government data through several government portals. It also documents MCP tools, REST APIs, tests, and project conventions.

In plain words
What is it for?
Use it to work on the civic data modules, run tests and type checks, start MCP or REST services, and deploy or verify the project's proxy.
Why use it?
It tells a coding agent where to look before editing and how to verify changes across the SDK's modules. This helps avoid breaking portal-specific behavior or shared code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is suryast/indonesia-civic-stack's own configuration. It tells Claude Code how to work on indonesia-civic-stack itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything indonesia-civic-stack configures →

Reuse

Borrowing it

Nothing to install: this file belongs to suryast/indonesia-civic-stack. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/suryast/indonesia-civic-stack/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/suryast/indonesia-civic-stack

Made for: Claude Code.

Wrote 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.

agentmods badge for indonesia-civic-stack CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/suryast/indonesia-civic-stack/claude-md/github.svg)](https://agentmods.dev/instructions/suryast/indonesia-civic-stack/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/suryast/indonesia-civic-stack/claude-md"><img src="https://agentmods.dev/badge/instructions/suryast/indonesia-civic-stack/claude-md/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.

agentmods 80×15 button for indonesia-civic-stack CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/suryast/indonesia-civic-stack/claude-md"><img src="https://agentmods.dev/badge/instructions/suryast/indonesia-civic-stack/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 475 This file is loaded in full into every session.
When invoked 475 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00475 $0.00475
Opus 5.5 $0.00190 $0.00190
Sonnet 5.5 $0.00095 $0.00095
Haiku 4.5 $0.00047 $0.00047

Measured 2mo ago against content hash 292084c38518, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

indonesia-civic-stack 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 2mo 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.

CLAUDE.md · 68 lines

What it actually says

CLAUDE.md — Instructions for Claude Code

MCP Integration

This repo includes .mcp.json — Claude Code auto-discovers 40 MCP tools on startup. The unified server (server.py) registers all tools from all 11 modules in one process.

Quick Context

This is a Python SDK for Indonesian government data. 11 modules, each wrapping a gov portal. Shared layer in civic_stack/shared/. Tests use VCR (no live calls). All async, Pydantic v2, Python 3.11+.

Before Writing Code

  1. Read AGENTS.md for architecture and patterns
  2. Read CONTRIBUTING.md for the module contract
  3. Check the module's README.md for portal-specific quirks
  4. Check GitHub issues for known portal changes

Commands

# Test
pytest -v
pytest tests/<module>/ -v

# Lint + format
ruff check . && ruff format --check .

# Type check
mypy civic_stack/

# Run unified MCP server (40 tools)
python server.py

# Run single module MCP server
python -m civic_stack.bpom.server

# Run single module REST API
uvicorn civic_stack.bpom.app:app --port 8001

# Run unified REST API
uvicorn app:app --port 8000

# Build & deploy proxy
cd proxy && npx wrangler deploy

# Verify MCP tools load
python -c "import asyncio; from server import mcp; print(asyncio.run(mcp.list_tools()))"

Do Not

  • Create raw httpx.AsyncClient — use civic_client()
  • Raise exceptions from search() — return error_response() envelope
  • Hit live portals in tests — record VCR cassettes
  • Modify civic_stack/shared/schema.py without checking all 11 modules
  • Remove proxy_url parameter from any function signature
  • Use print() — use logger from logging

Style

  • Line length: 100
  • Async-first: async def, httpx.AsyncClient
  • Type hints on all public functions
  • Pydantic v2 models
  • ruff for linting and formatting
Changes

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.

  1. 2mo ago First seen · 68 lines · 475 tokens per session scan A 292084c38518

Subscribe to this mod's changes

indonesia-civic-stack CLAUDE.md is an instructions file published in the GitHub repository suryast/indonesia-civic-stack (12 stars, last pushed 4d ago), licensed MIT. It adds 475 tokens to every session, about $0.0019 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 2026-08-31.

Related

indonesia-civic-stack CLAUDE.md compared with instructions from other repositories

indonesia-civic-stack CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
indonesia-civic-stack CLAUDE.mdsuryast/indonesia-civic-stackInstructions file124d agoMITA475Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode