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 skills add mpsuesser/pi-effect-harness --skill effect-domain-predicatesgit clone --depth 1 https://github.com/mpsuesser/pi-effect-harnessWrote 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/skills/mpsuesser/pi-effect-harness/effect-domain-predicates)<a href="https://agentmods.dev/skills/mpsuesser/pi-effect-harness/effect-domain-predicates"><img src="https://agentmods.dev/badge/skills/mpsuesser/pi-effect-harness/effect-domain-predicates.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 | $0.00018 | $0.05878 |
| Opus 5 | $0.00009 | $0.02939 |
| Sonnet 5 | $0.00004 | $0.01176 |
| Haiku 4.5 | $0.00002 | $0.00588 |
Grade A, and why
effect-domain-predicates 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 8d 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 — 868 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain Predicates Skill
Generate complete sets of predicates and Order instances for domain types, derived from typeclass implementations.
Effect Source Reference
The Effect v4 source is available at ~/.cache/effect-v4/.
Browse and read files there directly to look up APIs, types, and implementations.
Reference this for:
- Full Schema API:
packages/effect/SCHEMA.md - Order source:
packages/effect/src/Order.ts - Equivalence source:
packages/effect/src/Equivalence.ts - Predicate source:
packages/effect/src/Predicate.ts - Effect source:
packages/effect/src/
Pattern: Deep Structural Equality (v4)
In v4, Equal.equals performs deep structural comparison by default — no special wrapping is needed:
import { Schema, Equal, DateTime } from 'effect';
export const Task = Schema.TaggedStruct('pending', {
id: Schema.String,
createdAt: Schema.DateTimeUtc
});
export type Task = Schema.Schema.Type<typeof Task>;
declare const makeTask: (props: {
id: string;
createdAt: DateTime.Utc;
}) => Task;
declare const now: DateTime.Utc;
// Usage: Deep structural equality (automatic in v4)
const task1 = makeTask({ id: '123', createdAt: now });
const task2 = makeTask({ id: '123', createdAt: now });
Equal.equals(task1, task2); // true - deep structural equality
Pattern: Equivalence from Schema
When you need an Equivalence instance (for use with combinators), derive it from the schema:
import { Schema, Array } from 'effect';
import * as Equivalence from 'effect/Equivalence';
declare const Task: Schema.Schema<any, any, never>;
type Task = Schema.Schema.Type<typeof Task>;
// Derive from schema (structural equality)
export const TaskEquivalence = Schema.toEquivalence(Task);
declare const tasks: Array<Task>;
// Usage with combinators
const uniqueTasks = Array.dedupeWith(tasks, TaskEquivalence);
Pattern: Field-Based Equivalence with Equivalence.mapInput
Compare by specific fields using Equivalence.mapInput:
import { DateTime } from 'effect';
import * as Equivalence from 'effect/Equivalence';
interface Task {
readonly _tag: string;
readonly id: string;
readonly createdAt: DateTime.Utc;
}
/**
* Compare tasks by ID only.
*
* @category Equivalence
* @since 0.1.0
* @example
* import * as Task from "@/schemas/Task"
* import * as Array from "effect/Array"
*
* const uniqueById = Array.dedupeWith(tasks, Task.EquivalenceById)
*/
export const EquivalenceById = Equivalence.mapInput(
Equivalence.String,
(task: Task) => task.id
);
/**
* Compare by status tag.
*
* @category Equivalence
* @since 0.1.0
*/
export const EquivalenceByTag = Equivalence.mapInput(
Equivalence.String,
(task: Task) => task._tag
);
/**
* Compare by creation date.
*
* @category Equivalence
* @since 0.1.0
*/
export const EquivalenceByCreatedAt = Equivalence.mapInput(
DateTime.Equivalence,
(task: Task) => task.createdAt
);
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.
- 8d ago First seen · 868 lines · 18 tokens per session scan A c872020cdd35
effect-domain-predicates is a skill published in the GitHub repository mpsuesser/pi-effect-harness (24 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 5,878 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
effect-patterns-concurrency
Effect-TS patterns for Concurrency. Use when working with concurrency in Effect-TS applications.
effect-patterns-making-http-requests
Effect-TS patterns for Making Http Requests. Use when working with making http requests in Effect-TS applications.
effect-patterns-streams
Effect-TS patterns for Streams. Use when working with streams in Effect-TS applications.
effect-patterns-error-handling
Effect-TS patterns for Error Handling. Use when working with error handling in Effect-TS applications.
effect-patterns-streams-sinks
Effect-TS patterns for Streams Sinks. Use when working with streams sinks in Effect-TS applications.
effect-patterns-resource-management
Effect-TS patterns for Resource Management. Use when working with resource management in Effect-TS applications.