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 skills/mpsuesser/pi-effect-harness/effect-http-servernpx skills add mpsuesser/pi-effect-harness --skill effect-http-servergit 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-http-server)<a href="https://agentmods.dev/skills/mpsuesser/pi-effect-harness/effect-http-server"><img src="https://agentmods.dev/badge/skills/mpsuesser/pi-effect-harness/effect-http-server.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 | $0.00084 | $0.10602 |
| Opus 5 | $0.00042 | $0.05301 |
| Sonnet 5 | $0.00017 | $0.02120 |
| Haiku 4.5 | $0.00008 | $0.01060 |
Grade A, and why
effect-http-server 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 4d 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 — 907 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Effect TypeScript expert specializing in HTTP servers built with effect/unstable/http — HttpRouter, HttpServer, HttpServerRequest, HttpServerResponse, HttpMiddleware, and the platform server layers.
This skill covers the imperative HTTP server primitives. For the declarative, schema-first HttpApi/OpenAPI layer see the effect-http-api skill; for HTTP clients see effect-http-client; for raw TCP/WebSocket sockets see effect-socket.
Effect Source Reference
The Effect v4 source is at ~/.cache/effect-v4/. Read it directly when in doubt — these modules are unstable and change between betas.
Key files:
packages/effect/src/unstable/http/HttpRouter.ts— router service,add/addAll/route/use,serve,toWebHandler, schema decoders,middleware,cors,provideRequest,RouterConfigpackages/effect/src/unstable/http/HttpServer.ts—HttpServerservice,serve/serveEffect, address helpers,layerTestClient,layerServicespackages/effect/src/unstable/http/HttpServerRequest.ts— request model, body accessors,schemaBodyJson/schemaBodyForm/etc.,ParsedSearchParams,upgrade,MaxBodySizepackages/effect/src/unstable/http/HttpServerResponse.ts— every response constructor and combinator,toWeb/fromWebpackages/effect/src/unstable/http/HttpMiddleware.ts—logger,tracer,cors,xForwardedHeaders,searchParamsParser, tracing config referencespackages/effect/src/unstable/http/HttpEffect.ts—toWebHandler*,fromWebHandler,toHandled, pre-response handlers, request scope managementpackages/effect/src/unstable/http/HttpServerError.ts—HttpServerError+ reasons,causeResponse,ClientAbortpackages/effect/src/unstable/http/HttpServerRespondable.ts— the error-to-response protocolpackages/effect/src/unstable/http/HttpBody.ts— body variants (Empty/Raw/Uint8Array/FormData/Stream) and constructorspackages/effect/src/unstable/http/Headers.ts,Cookies.ts,Multipart.ts— header/cookie/multipart models and limitspackages/effect/src/unstable/http/HttpStaticServer.ts— static file servingpackages/platform-node/src/NodeHttpServer.ts— Node server adapter,layer,layerTest, graceful shutdownpackages/platform-bun/src/BunHttpServer.ts— Bun equivalentpackages/platform-node/test/NodeHttpServer.test.ts— the best end-to-end reference for real route/middleware/multipart wiring
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.
- 4d ago First seen · 907 lines · 84 tokens per session scan A c798817eed76
effect-http-server is a skill published in the GitHub repository mpsuesser/pi-effect-harness (23 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 10,602 once invoked, about $0.0004 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
gh-pr-description
Drafts and reviews GitHub pull request descriptions for the eve repository. Use when opening, updating, or reviewing a PR, or when summarizing a branch for reviewers.
technical-writing
Write, edit, review, or audit user-facing documentation for the eve repository. Use for changes under docs/, documentation tied to eve APIs or CLI behavior, docs work based on Slack or support feedback, and requests to make eve docs clearer, more natural, or less AI-patterned while verifying claims against current…
toolkit-guide
How to triage an account and verify packaged skill resources with the toolkit CRM extension.
local-guide
The consuming agent's own guide skill.
codebase-memory
Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions…
using-pi-subagents
Operate pi-subagents jobs safely, including direct-work decisions, least-privilege tool selection, thinking-level selection, delegation, bidirectional messaging, parallel starts, timeout selection, waiting, cancellation, result handling, verification, and writer isolation.