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 daydreamsai/lucid-agents --skill 1.0.1git clone --depth 1 https://github.com/daydreamsai/lucid-agentsWrote 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/daydreamsai/lucid-agents/1.0.1)<a href="https://agentmods.dev/skills/daydreamsai/lucid-agents/1.0.1"><img src="https://agentmods.dev/badge/skills/daydreamsai/lucid-agents/1.0.1/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/daydreamsai/lucid-agents/1.0.1"><img src="https://agentmods.dev/badge/skills/daydreamsai/lucid-agents/1.0.1.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 | $0.00075 | $0.01263 |
| Opus 5 | $0.00037 | $0.00632 |
| Sonnet 5 | $0.00015 | $0.00253 |
| Haiku 4.5 | $0.00007 | $0.00126 |
Grade A, and why
lucid-agents 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 11d 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.
This is a copy
100% identical to lucid-agents — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lucid Agents
Use this skill to make changes that match the installed Lucid release channel and preserve the framework's extension-owned architecture. Inspect the project before proposing code; package versions and generated adapter shape are part of the API.
Start with project evidence
Run the bundled inspector from the skill directory:
node scripts/inspect-project.mjs /absolute/path/to/project
Read its JSON before editing. Also inspect the project's package.json, lockfile, AGENTS.md, agent builder, adapter bootstrap, entrypoint definitions, and service-ui.config.ts when present.
Treat its channel result as a guardrail:
stable: use APIs present in the installed registry package versions.next: use the checked-out workspace source and package READMEs as truth.mixed: stop implementation until the user selects registry packages or local/workspace packages consistently.unknown: locate the actual Lucid dependency source before writing SDK code.
Never silently upgrade packages, replace an adapter, add a payment protocol, or change a public route. State such changes explicitly and get authorization when they expand the request.
Use the source-of-truth order
When examples disagree, prefer evidence in this order:
- Installed TypeScript declarations and package source for the project's exact version.
- Package README and tests for that same version or checkout.
- Generated template files and their local
AGENTS.md. - This skill's references.
- General documentation, blog posts, or memory.
Do not invent an API to reconcile conflicting examples. Explain the version mismatch and choose the form supported by the project.
Preserve the runtime model
- Compose capabilities with
createAgent(...).use(extension()).build(). - Let each domain package own its runtime behavior and configuration.
- Register every public operation once as a typed entrypoint.
- Let adapters bind
runtime.http.routesor delegate toruntime.http.handlers. - Do not create adapter-local registries, paywalls, manifests, or authorization flows.
- Keep secrets server-side and read them from environment variables.
- Use durable stores for production state that must survive process restarts.
- Prefer the project's existing package versions and patterns over a broad refactor.
What ships with it
15 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.
- agents/openai.yaml 189 B
- LICENSE.txt 1.1 KB
- references/adapters-scaffolding.md 1.4 KB
- references/contributor-architecture.md 1.5 KB
- references/deployment-production.md 1.3 KB
- references/discovery-tasks.md 1.3 KB
- references/identity-wallets.md 1.4 KB
- references/mpp.md 1.4 KB
- references/release-channels.md 1.5 KB
- references/runtime-entrypoints.md 1.5 KB
- references/service-ui.md 1.1 KB
- references/troubleshooting.md 1.7 KB
- references/x402-payments.md 1.6 KB
- scripts/inspect-project.mjs 3.4 KB runs code
- VERSION 6 B
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.
- 11d ago First seen · 105 lines · 75 tokens per session scan A 24ce74fef21c
lucid-agents is a skill published in the GitHub repository daydreamsai/lucid-agents (196 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,263 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to lucid-agents, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
near-api-js
Guide for developing with near-api-js v7 - the JavaScript/TypeScript library for NEAR blockchain interaction. Use when: (1) building apps that interact with NEAR blockchain, (2) creating/signing transactions, (3) calling smart contracts, (4) managing accounts and keys, (5) working with NEAR RPC API, (6) handling…
near-kit
TypeScript library for NEAR Protocol blockchain interaction. Use this skill when writing code that interacts with NEAR Protocol, including viewing contract data, calling contract methods, sending NEAR tokens, building transactions, creating type-safe contract wrappers, integrating wallets (Wallet Selector, HOT…
blocks-getstarted
Linear first-time quickstart for building a brand-new Blocks Network agent. Walks the LLM through ask-name → scaffold → register → run end-to-end. Defaults to TypeScript; use Python only on explicit request.
adk-sample-creator
Author or rework a runnable example under examples/ in the ADK Go repository — the directory, main.go, the README with its Mermaid diagram and real transcript, and the index row. Use when adding a sample for a feature (workflow graph, tool, registry client, model backend, server), when asked to "add an example" for…
chat-sdk
Build multi-platform chat bots with Chat SDK (chat npm package). Use when developers want to (1) Build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, (2) Use Chat SDK to handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files, or AI…
azure-identity-ts
Authenticate to Azure services using Azure Identity library for JavaScript (@azure/identity). Use when configuring authentication with DefaultAzureCredential, managed identity, service principals, or interactive browser login.