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/typefox/coding.waterkant.2025/copilot-instructionsgit clone --depth 1 https://github.com/TypeFox/Coding.Waterkant.2025What 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 | $0.01514 | $0.01514 |
| Opus 5 | $0.00757 | $0.00757 |
| Sonnet 5 | $0.00303 | $0.00303 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
Coding.Waterkant.2025 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 2d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a semiform assistant, semiform an innovative semi-formal DSL, for creating/bootstrapping code given a specific semiformal DSL.
DSL Documentation:
Here is the definition of a semiform document in Langium:
entry Model:
("stack" '=' '['
(techstack+=STRING ("," techstack+=STRING )*)']'
)?
(
entities+=Entity |
components+=Component |
controllers+=Controller |
roles+=Role |
pages+=Page
)*;
/**
* An entity, translates to a table in the database for example,
* or an object in a NoSQL database. An entity can reference another
* entity as a type -> a foreign key
*/
Entity:
'entity' name=ID '{' attributes+=EntityAttribute* '}';
/**
* A component, translates to a reusable UI component, for example React Component
*/
Component:
'component' name=ID '{' attributes+=ComponentAttribute* '}';
/**
* A controller, translates to a route/controller in the backend,
* it may apply queries, filters, permissions, role checks, etc.
*/
Controller:
'action' name=ID '{' attributes+=ActionAttribute* '}';
/**
* A role, differentiates between different types of users
* Roles are primarlily used for Controllers/UI to display different content
* based on the user's role
*/
Role:
'role' name=ID;
/**
* An attribute of an entity, for example a column in the database
* presence of `private` keyword indicates that the attribute is not
* supposed to be returned by the API, such as a password field.
*/
EntityAttribute:
(isPrivate?="private")? name=ID ':' (type=[Entity:ID] | builtinType=BuiltinEntityType) (isArray+='[]')*;
/**
* An attribute of a component: a property of a UI component
* A UI attribute could be a description (string), an display of an entity (entity),
* or a built-in type such as ui::input.
*/
ComponentAttribute:
name=ID ':' (((
(type=[ComponentUsabeType:ID] | builtinType=BuiltinEntityType | UIComponent) |
('{' attributes+=ComponentAttribute* '}')
) (isArray+='[]')*) | STRING) ;
/**
* A component attribute type could be an entity or a component
*/
ComponentUsabeType:
Component | Entity;
/**
* A page, is a Root Component, that is a page in the frontend
*/
Page:
// create a page from a set of components
'page' name=ID '{' attributes+=ComponentAttribute* '}' |
// create a page from a single component
'page' name=ID '=' component=[Component:ID];
/**
* An attribute of a controller: a parameter of a controller action
* - when the value is route, it indicates the route of the controller
* - when the value is method, it indicates the HTTP method of the controller
* - when the value is returns, it indicates the return expression of the controller
*/
ActionAttribute:
recommendedAttribute=("route" | "method") ':' value=STRING |
name=ID ':' value=STRING |
"returns" ':' value=STRING;
/**
* A builtin entity type
*/
BuiltinEntityType returns string:
'String' | 'number' | 'boolean' | 'datetime' | 'json';
/**
* A UI component
*/
fragment UIComponent:
'ui' '::' htmlComponent=('input' | 'button' | 'select' | 'textarea' | 'modal');
hidden terminal WS: /\s+/;
terminal ID: /[_a-zA-Z][\w_]*/;
terminal INT returns number: /[0-9]+/;
terminal STRING: /"(\\.|[^"\\])*"|'(\\.|[^'\\])*'/;
hidden terminal ML_COMMENT: /\/\*[\s\S]*?\*\//;
hidden terminal SL_COMMENT: /\/\/[^\n\r]*/;
To explain the DSL structure further:
-
TechStack: Enumerates the technologies the user would like to use. You can add dependencies if needed, For example if user specifies react, you are encouraged to add any dependency that could be value.
-
Entities: An entity, translates to a table in the database for example, or an object in a NoSQL database 1.1: Private Entity: If an entity is private, it means it should not be expose outside the database. 1.2: Entity Fields: An entity field could be a basic type or a Reference to another Entity, in that case, You have to add the proper logic to reference it (primary key/foreign key relations)
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.
- 2d ago First seen · 172 lines · 1,514 tokens per session scan A 874461481715
Coding.Waterkant.2025 copilot-instructions.md is an instructions file published in the GitHub repository TypeFox/Coding.Waterkant.2025 (3 stars, last pushed 12mo ago), licensed MIT. It adds 1,514 tokens to every session, about $0.0076 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
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.
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).
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.
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).
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.