Borrowing it
Nothing to install: this file belongs to gulmezeren2-byte/andon. 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/gulmezeren2-byte/andon/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/gulmezeren2-byte/andonWrote 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/gulmezeren2-byte/andon/copilot-instructions)<a href="https://agentmods.dev/instructions/gulmezeren2-byte/andon/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/gulmezeren2-byte/andon/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 | $0.00969 | $0.00969 |
| Opus 5 | $0.00485 | $0.00485 |
| Sonnet 5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
andon 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 6d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot instructions — andon
Deterministic verifier that re-checks the numbers in a finished report or workbook against their source data using arithmetic — reconciliation, internal consistency, schema contracts, Excel integrity — never a second LLM. Python 3.10+, managed with uv (hatchling backend); the PyPI distribution is andon-verify but the import package and CLI stay andon.
Build, test, lint
uv sync --dev # CI adds: --extra duckdb --extra mcp (so those tests run, not skip)
uv run pytest # real CSV/XLSX fixtures, no mocks
uv run ruff check src tests # line-length 100; select E,F,I,UP,B,SIM,RET,C4
uv run mypy src # disallow_untyped_defs = true
uv run python scripts/make_demo_svg.py # regenerate docs/demo.svg if demo output changed (same PR)
CLI: andon run spec.yaml [--json --strict --md out.md], andon inspect x.xlsx, andon diff a.xlsx b.xlsx, andon init. MCP front end: andon-mcp (tools run, inspect, diff). CI (Linux + Windows, py3.10 & 3.14) also asserts the sabotaged examples/quarterly-report exits 1.
Architecture
A run is "YAML spec in -> Report out". spec.py parses the spec (each check entry has exactly one dotted kind like reconcile.sum; only name/id/skip are also allowed; relative paths resolve against the spec file's dir). sources.py (SourceStore) loads CSV/Excel/parquet/DuckDB/JSON and resolves each check "side". engine.py runs every check in its own try/except (one bad check never aborts the run; exceptions become ERROR findings) and returns a Report. result.py holds Status (PASS/FAIL/REVIEW/SKIP/ERROR), Report.verdict, and Report.exit_code(). render.py emits terminal/JSON/Markdown; cli.py (typer + rich) and mcp_server.py are the two front ends; diff.py powers andon diff.
Structure
src/andon/checks/— one module per family (reconcile,internal,schema,excel_integrity,plausibility);checks/__init__.pyis the registry plus shared param helpers.tests/— one file per module; fixturesorders_csv,workbook_factory,run_speclive inconftest.py.docs/checks.md(full parameter reference) ·examples/quarterly-report/(demo) ·skills/verify-with-andon/(agent skill) ·action.yml/Dockerfile/.pre-commit-hooks.yaml(integrations).
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.
- 6d ago First seen · 36 lines · 969 tokens per session scan A d43848c6b6a2
andon copilot-instructions.md is an instructions file published in the GitHub repository gulmezeren2-byte/andon (1 stars, last pushed 1mo ago), licensed MIT. It adds 969 tokens to every session, about $0.0048 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
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.
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).
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).
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.
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.