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 eric-cielo/moflo --skill spell-buildergit clone --depth 1 https://github.com/eric-cielo/mofloWrote 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/eric-cielo/moflo/spell-builder)<a href="https://agentmods.dev/skills/eric-cielo/moflo/spell-builder"><img src="https://agentmods.dev/badge/skills/eric-cielo/moflo/spell-builder/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/eric-cielo/moflo/spell-builder"><img src="https://agentmods.dev/badge/skills/eric-cielo/moflo/spell-builder.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 | $0.00046 | $0.03208 |
| Opus 5.5 | $0.00018 | $0.01283 |
| Sonnet 5.5 | $0.00009 | $0.00642 |
| Haiku 4.5 | $0.00005 | $0.00321 |
Grade B, and why
spell-builder scanned grade B 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 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
To find available steps, `Glob` `.claude/skills/spell-builder/steps/*/README.md` and read each H1. How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spell Builder
Purpose: produce production-ready spell definitions (YAML/JSON) that compose step commands and connectors into end-to-end automated spells, with proper data flow, validation, and engine integration.
Read First — Companion Files
| File | When to read |
|---|---|
| architecture.md | Always — three-layer model (spell → step → connector); putting logic in the wrong layer is the most common mistake |
| permissions.md | When defining or editing any step — required disclosure & dry-run report format |
| preflight.md | When the step depends on runtime state (clean git tree, logged-in CLI, reachable host) |
Prerequisites
- MoFlo project with
cli/spellspackage - Familiarity with YAML syntax
Quick Start
Ask the user:
What would you like to do?
- Create a new spell definition from scratch
- Edit an existing spell definition
- Discover available step commands and connectors
- Validate an existing spell file
Then follow the appropriate section below.
Section 1: Create a New Spell
Step 1: Gather Spell Metadata
| Field | Required | Example |
|---|---|---|
| Name | Yes (kebab-case) | deploy-staging, security-audit |
| Description | Recommended | Deploy to staging with smoke tests |
| Version | Optional (default 1.0) |
1.0 |
| Abbreviation | Optional | ds (short lookup key for /flo -wf ds) |
| MoFlo Level | Optional (default none) |
none, memory, hooks, full, recursive |
Step 2: Define Arguments (Optional)
If the spell needs runtime parameters, define each argument:
| Field | Required | Description |
|---|---|---|
| Name | Yes | Argument identifier (e.g., target, severity) |
| Type | Yes | string, number, boolean, or string[] |
| Required | Optional (default false) |
Whether the argument must be provided |
| Default | Optional | Default value if not provided |
| Enum | Optional | Allowed values (e.g., [low, medium, high]) |
| Description | Optional | Help text |
What ships with it
18 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.
- architecture.md 8.5 KB
- connectors/github-cli/README.md 2.0 KB
- connectors/http/README.md 1.4 KB
- connectors/local-outlook/README.md 1.9 KB
- connectors/playwright/README.md 1.7 KB
- permissions.md 4.3 KB
- preflight.md 4.1 KB
- steps/agent/README.md 1.8 KB
- steps/bash/README.md 1005 B
- steps/browser/README.md 2.1 KB
- steps/condition/README.md 1.1 KB
- steps/github/README.md 1.6 KB
- steps/loop/README.md 1.2 KB
- steps/memory/README.md 1.6 KB
- steps/outlook/README.md 2.9 KB
- steps/parallel/README.md 1.1 KB
- steps/prompt/README.md 923 B
- steps/wait/README.md 667 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.
- 1mo ago First seen · 337 lines · 46 tokens per session scan B 3698639a3911
spell-builder is a skill published in the GitHub repository eric-cielo/moflo (19 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 3,208 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
johnny-suede-design
Suede AI full-stack surface builder that runs design, copy, and visual QA as one pass: landing pages, brand surfaces, product UI, dashboards, campaigns, launch pages, and reference-to-target restyles (suedify). Use when a build needs layout and words together, when a redesign or launch surface has to ship end to end…
suede-code-review
Suede AI findings-only code review with full context: changed files, callers, contracts, and deploy surface. Covers TypeScript, React, Next.js, database, Swift/iOS, OWASP, accessibility, SEO, observability, commit hygiene, and deploy risk, ranked P0-P3 with file:line evidence and a fix path. Use when asked to review a…
voice-preserving-line-edit
Context-aware line edit that strips generic AI writing patterns without flattening the author's voice, plus a findings-only audit mode that names issues instead of rewriting. Applies contextual rules rather than blanket bans on adverbs, passive voice, and punctuation, and locks facts, numbers, quotes, code, links, and…
suede-aso
Suede-owned app-store optimization discipline for keyword fields, titles, subtitles, descriptions, screenshots, ratings context, and competitor listing audits. Use when improving App Store or Google Play visibility or listing conversion from a live app URL and current console evidence, or when authoring keyword, name…
suede-clip-to-guide
Suede-owned short-to-long content funnel blueprint. Use when turning a video, clip, interview moment, talk excerpt, screen recording, or transcript into a repeatable package that bridges attention to an X Article, LinkedIn article, newsletter, blog guide, or playbook, or when third-party footage needs a rights route…
suede-prospecting
Suede-owned prospecting and qualification discipline. Use when defining an ICP, sourcing and enriching a bounded lead list, finding early adopters or design partners, scoring account fit, or documenting disqualification evidence. NOT FOR: sending outreach (use suede-cold-email), changing CRM routing (use…