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/suryast/indonesia-civic-stack/copilot-instructionsgit clone --depth 1 https://github.com/suryast/indonesia-civic-stackWrote 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/suryast/indonesia-civic-stack/copilot-instructions)<a href="https://agentmods.dev/instructions/suryast/indonesia-civic-stack/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/suryast/indonesia-civic-stack/copilot-instructions.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 | $0.00248 | $0.00248 |
| Opus 5 | $0.00124 | $0.00124 |
| Sonnet 5 | $0.00050 | $0.00050 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
indonesia-civic-stack copilot-instructions.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 5d 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.
What it actually says
Copilot Instructions
This is a Python SDK for Indonesian government data portals.
Key rules:
- All functions are async. Use
async defandawait. - Always use
civic_client()fromshared.http— never raw httpx. - Every function must accept
proxy_url: str | None = Noneparameter. - Return
CivicStackResponsefromshared.schema— never raw dicts. - On errors, return
error_response()— never raise insearch(). - Rate limit with
RateLimiterfromshared.http. - Tests use VCR cassettes — never hit live government portals.
- Python 3.11+, Pydantic v2, ruff for formatting, line length 100.
File structure per module:
scraper.py— fetch() and search() functionsnormalizer.py— raw HTML/JSON → dict transformationsrouter.py— FastAPI routesserver.py— MCP server using CivicStackMCPBaseapp.py— FastAPI appREADME.md— module docs
See AGENTS.md for full architecture guide.
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.
- 5d ago First seen · 24 lines · 248 tokens per session scan A c8662475a4cf
indonesia-civic-stack copilot-instructions.md is an instructions file published in the GitHub repository suryast/indonesia-civic-stack (6 stars, last pushed 25d ago), licensed MIT. It adds 248 tokens to every session, about $0.0012 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 2026-08-31.
Other instructions, from other repositories
curb CLAUDE.md
Claude Code instructions for alevizio/curb, covering curb — sf street parking, block by block, what it is, stack (intentionally minimal), spatial queries (verified working) and key product decisions / constraints (don't regress these).
curb AGENTS.md
AGENTS.md instructions for alevizio/curb, covering curb — sf street parking, block by block, what it is, stack (intentionally minimal), spatial queries (verified working) and key product decisions / constraints (don't regress these).
ph-civic-data-mcp CLAUDE.md
Claude Code instructions for xmpuspus/ph-civic-data-mcp, covering claude.md - ph-civic-data-mcp, what this is, contracts every change must hold, registration and module layout and psa openstat landmines.
forthepeople CLAUDE.md
Claude Code instructions for jayanthmb14/forthepeople, covering claude.md — forthepeople.in project instructions, project, database schema changes (critical — changed june 2026), documentation location and completed prompts archive.
civic-ai-tools AGENTS.md
AGENTS.md instructions for npstorey/civic-ai-tools, covering agents.md, boundaries, commands, mcp configuration and where the detail lives.
civ.iq CLAUDE.md
Claude Code instructions for civdotiq/civ.iq, covering claude.md - civ.iq ai assistant instructions, quick context, critical rules (never violate), project structure and domain rules (in .claude/rules/).