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-parallelizationgit 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-parallelization)<a href="https://agentmods.dev/skills/mpsuesser/pi-effect-harness/effect-parallelization"><img src="https://agentmods.dev/badge/skills/mpsuesser/pi-effect-harness/effect-parallelization/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mpsuesser/pi-effect-harness/effect-parallelization"><img src="https://agentmods.dev/badge/skills/mpsuesser/pi-effect-harness/effect-parallelization.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00079 | $0.07139 |
| Opus 5.5 | $0.00032 | $0.02856 |
| Sonnet 5.5 | $0.00016 | $0.01428 |
| Haiku 4.5 | $0.00008 | $0.00714 |
Grade A, and why
effect-parallelization 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 1mo 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 — 674 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 declarative concurrency — Effect.all, Effect.forEach, racing, and the coordination primitives Semaphore, PartitionedSemaphore, and Latch.
Effect Source Reference
The Effect v4 source is at ~/.cache/effect-v4/. Read it directly when in doubt — Effect v4 differs substantially from v3 and from most training data.
Key files:
packages/effect/src/Effect.ts—all,forEach,race/raceAll/raceFirst/raceAllFirst,firstSuccessOf,timeout/timeoutOption/timeoutOrElse,zip/zipWith,filter/filterMap/filterMapEffect,partition,validate,findFirst,replicate/replicateEffect,withConcurrency(very large file — grep for the export, then read its JSDoc)packages/effect/src/Types.ts— theConcurrencytype (number | "unbounded" | "inherit")packages/effect/src/References.ts—CurrentConcurrencyreference read by"inherit"packages/effect/src/Semaphore.ts— counting semaphore:make,withPermit(s),withPermitsIfAvailable,take/release/releaseAll,resizepackages/effect/src/PartitionedSemaphore.ts— keyed permit pool with round-robin fairness across partitionspackages/effect/src/Latch.ts— open/closed gate:make,open,close,release,await,whenOpenpackages/effect/src/internal/effect.ts— the actual implementations (forEachConcurrent,raceAll, ...) when you need exact semanticspackages/effect/test/Effect.test.ts—forEach/all/partition/validate/raceAlldescribe blocks with interruption edge casespackages/effect/test/Semaphore.test.ts,test/PartitionedSemaphore.test.ts,test/Latch.test.ts— real usage withTestClockmigration/v3-to-v4.md— rename map (e.g.Effect.makeSemaphore→Semaphore.make)
Core Model
Concurrency in Effect is declarative: combinators that operate on many effects take a concurrency option, fork child fibers internally, and uphold structured concurrency — when the combined effect finishes, fails, or is interrupted, every in-flight child fiber is interrupted before the result is produced.
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.
- 1mo ago First seen · 674 lines · 79 tokens per session scan A f729d65c348f
effect-parallelization is a skill published in the GitHub repository mpsuesser/pi-effect-harness (25 stars, last pushed 4mo ago), licensed MIT. It adds 79 tokens to every session and 7,139 once invoked, about $0.0003 per session on Opus 5.5. 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-streams-sinks
Effect-TS patterns for Streams Sinks. Use when working with streams sinks 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-resource-management
Effect-TS patterns for Resource Management. Use when working with resource management in Effect-TS applications.