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/atopile/packages/atogit clone --depth 1 https://github.com/atopile/packagesWhat 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 | $0.05154 | $0.05154 |
| Opus 5 | $0.02577 | $0.02577 |
| Sonnet 5 | $0.01031 | $0.01031 |
| Haiku 4.5 | $0.00515 | $0.00515 |
Grade A, and why
packages ato.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 today.
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 — 712 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ato is a declarative DSL to design electronics (PCBs) with. It is part of the atopile project. Atopile is run by the vscode/cursor/windsurf extension. The CLI (which is invoked by the extension) actually builds the project.
Not available in ato
- if statements
- while loops
- functions (calls or definitions)
- classes
- objects
- exceptions
- generators
Ato Syntax
ato sytax is heavily inspired by Python, but fully declarative. ato thus has no procedural code, and no side effects.
Examples of syntax
#pragma text
#pragma func("X")
# enable for loop syntax feature:
#pragma experiment("FOR_LOOP)
# --- Imports ---
# Standard import (newline terminated)
import ModuleName
# Import with multiple modules (newline terminated)
import Module1, Module2.Submodule
# Import from a specific file/source (newline terminated)
from "path/to/source.ato" import SpecificModule
# Multiple imports on one line (semicolon separated)
import AnotherModule; from "another/source.ato" import AnotherSpecific
# Deprecated import form (newline terminated)
# TODO: remove when unsupported
import DeprecatedModule from "other/source.ato"
# --- Top-level Definitions and Statements ---
pass
pass;
"docstring-like statement"
"docstring-like statement";
top_level_var = 123
# Compound statement
pass; another_var = 456; "another docstring"
# Block definitions
component MyComponent:
# Simple statement inside block (newline terminated)
pass
# Multiple simple statements on one line (semicolon separated)
pass; internal_flag = True
module AnotherBaseModule:
pin base_pin
base_param = 10
interface MyInterface:
pin io
module DemoModule from AnotherBaseModule:
# --- Declarations ---
pin p1 # Pin declaration with name
pin 1 # Pin declaration with number
pin "GND" # Pin declaration with string
signal my_signal # Signal definition
a_field: AnotherBaseModule # Field declaration with type hint
# --- Assignments ---
# Newline terminated:
internal_variable = 123
# Semicolon separated on one line:
var_a = 1; var_b = "string"
# Cumulative assignment (+=, -=) - Newline terminated
value = 1
value += 1; value -= 1
# Set assignment (|=, &=) - Newline terminated
flags |= 1; flags &= 2
# --- Connections ---
p1 ~ base_pin
mif ~> bridge
mif ~> bridge ~> bridge
mif ~> bridge ~> bridge ~> mif
bridge ~> mif
mif <~ bridge
mif <~ bridge <~ bridge
mif <~ bridge <~ bridge <~ mif
bridge <~ mif
# Semicolon separated on one line:
p_multi1 ~ my_signal; p_multi2 ~ sig_multi1
# --- Retyping ---
instance.x -> AnotherBaseModule
# --- Instantiation ---
instance = new MyComponent
container = new MyComponent[10]
templated_instance_a = new MyComponent
templated_instance_b = new MyComponent<int_=1>
templated_instance_c = new MyComponent<float_=2.5>
templated_instance_d = new MyComponent<string_="hello">
templated_instance_e = new MyComponent<int_=1, float_=2.5, string_="hello">
templated_instance_f = new MyComponent<int_=1, float_=2.5, string_="hello", bool_=True>
# Semicolon separated instantiations (via assignment):
inst_a = new MyComponent; inst_b = new AnotherBaseModule
# --- Traits ---
trait trait_name
trait trait_name<int_=1>
trait trait_name<float_=2.5>
trait trait_name<string_="hello">
trait trait_name<bool_=True>
trait trait_name::constructor
trait trait_name::constructor<int_=1>
# Semicolon separated on one line:
trait TraitA; trait TraitB::constructor; trait TraitC<arg_=1>
# --- Assertions ---
assert x > 5V
assert x < 10V
assert 5V < x < 10V
assert x >= 5V
assert x <= 10V
assert current within 1A +/- 10mA
assert voltage within 1V +/- 10%
assert resistance is 1kohm to 1.1kohm
# Semicolon separated on one line:
assert x is 1V; assert another_param is 2V
# --- Loops ---
for item in container:
item ~ p1
# For loop iterating over a slice
for item in container[0:4]:
pass
item.value = 1; pass
# For loop iterating over a list literal of field references
for ref in [p1, x.1, x.GND]:
pass
# --- References and Indexing ---
# Reference with array index assignment
array_element = container[3]
# --- Literals and Expressions ---
# Integer
int_val = 100
neg_int_val = -50
hex_val = 0xF1
bin_val = 0b10
oct_val = 0o10
# Float
float_val = 3.14
# Physical quantities
voltage: V = 5V
resistance: ohm = 10kohm
capacitance: F = 100nF
# Bilateral tolerance
tolerance_val = 1kohm +/- 10%
tolerance_abs = 5V +/- 500mV
tolerance_explicit_unit = 10A +/- 1A
# Bounded quantity (range)
voltage_range = 3V to 3.6V
# Boolean
is_enabled = True
is_active = False
# String
message = "Hello inside module"
# Arithmetic expressions
sum_val = 1 + 2
diff_val = 10 - 3ohm
prod_val = 5 * 2mA
div_val = 10V / 2kohm # Results in current
power_val = 2**3
complex_expr = (5 + 3) * 2 - 1
flag_check = state | MASK_VALUE
# Comparisons
assert voltage within voltage_range
assert length <= 5mm
assert height >= 2mm
# --- Multi-line variations ---
pass; nested_var=1; another=2
complex_assignment = (
voltage + resistance
* capacitance
)
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.
- today First seen · 712 lines · 5,154 tokens per session scan A 336d5dc98c28
packages ato.instructions.md is an instructions file published in the GitHub repository atopile/packages (18 stars, last pushed 4mo ago), licensed MIT. It adds 5,154 tokens to every session, about $0.0258 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
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.
buildNext
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
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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
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.
langchain 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.