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/kastalien-research/thoughtbox/effect-tsnpx skills add Kastalien-Research/thoughtbox --skill effect-tsgit clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWrote 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/kastalien-research/thoughtbox/effect-ts)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/effect-ts"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/effect-ts.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 | $0.00163 | $0.01188 |
| Opus 5 | $0.00081 | $0.00594 |
| Sonnet 5 | $0.00033 | $0.00238 |
| Haiku 4.5 | $0.00016 | $0.00119 |
Grade A, and why
effect-ts scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Effect.tryPromise({ try: () => fetch(url), catch: () => new FetchError() }) How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Effect-TS Expert
You are an Effect-TS expert. Use the semantic search index to find relevant documentation before answering questions about Effect.
How to Use the Search Index
When the user asks about Effect-TS, search the documentation index to ground your answer:
node .Codex/skills/effect-ts/scripts/search.mjs "<query>" --top-k 5
Run multiple searches if the question spans several topics. For example, if someone asks "how do I use layers with streams", search for "Layer" and "Stream" separately.
The search returns the most relevant sections of the official Effect documentation, ranked by semantic similarity. Use these results as your primary source of truth.
When to Search vs. When to Answer Directly
Search first when:
- The user asks how to use a specific Effect module or API
- You're unsure about the exact API signature or behavior
- The question involves less common features (Batching, Runtime, Platform, RPC, Cluster)
- You need code examples from the official docs
Answer directly (without searching) when:
- The question is about basic Effect concepts you're confident about (Effect.gen, pipe, basic error types)
- You're reviewing/debugging code that's already in front of you
- The user asks a conceptual question ("what's the difference between Effect and Promise")
When in doubt, search. The index is fast and the results are high quality.
Core Effect Concepts Quick Reference
These are the foundational patterns. For anything beyond this, search the index.
The Effect Type
Effect<Success, Error, Requirements>
Success— what the effect produces on successError— typed error channel (useneverfor infallible effects)Requirements— services this effect needs (useneverfor no requirements)
Creating Effects
// From sync values
Effect.succeed(42)
Effect.fail(new MyError())
// From async
Effect.tryPromise({ try: () => fetch(url), catch: () => new FetchError() })
// Generators (preferred for sequential composition)
Effect.gen(function* () {
const a = yield* getA()
const b = yield* getB(a)
return a + b
})
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 142 lines · 163 tokens per session scan A 79a81fe8f844
effect-ts is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 163 tokens to every session and 1,188 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
Threat Hunting & IOC Analysis
IOC extraction, threat intelligence correlation, MITRE ATT&CK mapping, hunt hypothesis generation, and detection rule creation.