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/kitlangton/effect-solutions/claude-mdgit clone --depth 1 https://github.com/kitlangton/effect-solutionsWhat 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 | $0.01873 | $0.01873 |
| Opus 5 | $0.00937 | $0.00937 |
| Sonnet 5 | $0.00375 | $0.00375 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
effect-solutions CLAUDE.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 3d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Effect Solutions
Effect best practices and patterns for humans and AI agents — https://www.effect.solutions
Living Document: This is an opinionated collection exploiting Cunningham's Law ("the best way to get the right answer on the internet is not to ask a question; it's to post the wrong answer"). Disagree with a recommendation? Think we should cover something? Open an issue
Project Structure
packages/website/- Documentation site (Next.js)packages/cli/- CLI for local docs access.github/workflows/- Automated validation & bots
Quick Links
- Website: https://www.effect.solutions
- CLI:
bunx effect-solutions@latest list
Local Reference Repos
- Effect core monorepo (source for
@effect/*, including@effect/vitest/it.layer):/Users/kit/code/effectful/repos/effect
Development
bun install # Install dependencies
bun run dev # Website dev server
bun run dev:cli # CLI dev mode
bun run check # Biome (writes), tsc --build, tests
bun --cwd packages/website run format # Format website/docs
bun --cwd packages/website run generate:og # Rebuild Open Graph images
Open Graph Images
The Playwright generator lives at packages/website/scripts/generate-og.ts and renders the static template in packages/website/src/app/og/template/page.tsx. Run bun --cwd packages/website run generate:og to refresh every image (or OG_ONLY=slug1,slug2 bun --cwd packages/website run generate:og to target a subset). The resulting PNGs are written to packages/website/public/og/ and referenced automatically in the Next.js metadata.
Changesets & Publishing
bun scripts/changeset-named.ts "description" # Create named changeset
bun release # Version + tag packages, push tags for CI publish
Creating changesets:
- Use
bun scripts/changeset-named.ts "fix audio overlap"to create descriptive changeset files - Avoids random names like "purple-olives-look.md"
- Script prompts for package selection and change type interactively
- Resulting file:
.changeset/fix-audio-overlap.md
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.
- 3d ago First seen · 221 lines · 1,873 tokens per session scan A b24ee1d3b86f
effect-solutions CLAUDE.md is an instructions file published in the GitHub repository kitlangton/effect-solutions (435 stars, last pushed 4mo ago), licensed MIT. It adds 1,873 tokens to every session, about $0.0094 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 instructions, from other repositories
tevm CLAUDE.md
Claude Code instructions for evmts/tevm, covering tevm monorepo commands and style guide, project overview, forking implementation, json-rpc support and commands.
moss AGENTS.md
Instructions for D-Robotics/moss, covering agents.md, 仓库身份, 文档所有权与阅读顺序, 代码规范执行摘要（必须遵守） and 第一次进入仓库.
platform AGENTS.md
Instructions for dashpay/platform, covering repository guidelines, project structure & module organization, architecture, technology stack and key components.
agnix typescript.instructions.md
Instructions for agent-sh/agnix, covering typescript instructions and guidelines.
copperhead CLAUDE.md
Instructions for copperheadhq/copperhead, covering claude.md, what this repo is, sources of truth, workflow (openspec) and architecture (per spec.md §2).
openbridge-webcomponents docgen.instructions.md
Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering doc generator cli, it never edits the original and keep the prompt aligned with the rules.