agentmods.dev

fusion-tea: Skill for Claude Code

.agents/skills/formalize-intent/SKILL.md

formalize-intent is a skill for Claude Code from 1cFE/fusion-tea. It costs 19 tokens per session (1,611 once invoked), scanned A, original, MIT.

A process for turning unstructured descriptions of intent into documented goals and analysis questions. The results are placed in OVERVIEW.md, a project overview file.

In plain words
What is it for?
Use it to extract structured goals and questions from raw intent documents.
Why use it?
It makes vague requests easier to review and use as a basis for later system modeling and analysis.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code; installed under .agents/ (shared by several agents).

This is 1cFE/fusion-tea's own configuration. It tells Claude Code how to work on fusion-tea itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fusion-tea configures →

not rated 5repo changed 24d ago A scan 19 tokens original MIT
View source ↗ 1cFE/fusion-tea
Reuse

Borrowing it

Nothing to install: this file belongs to 1cFE/fusion-tea. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/1cFE/fusion-tea/main/.agents/skills/formalize-intent/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/1cFE/fusion-tea

Made for: Claude Code.

Wrote 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.

agentmods badge for formalize-intent

README.md
[![agentmods](https://agentmods.dev/badge/skills/1cfe/fusion-tea/formalize-intent/github.svg)](https://agentmods.dev/skills/1cfe/fusion-tea/formalize-intent)
Your own site
<a href="https://agentmods.dev/skills/1cfe/fusion-tea/formalize-intent"><img src="https://agentmods.dev/badge/skills/1cfe/fusion-tea/formalize-intent/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.

agentmods 80×15 button for formalize-intent

Your own site · 80×15
<a href="https://agentmods.dev/skills/1cfe/fusion-tea/formalize-intent"><img src="https://agentmods.dev/badge/skills/1cfe/fusion-tea/formalize-intent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,611 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.01611
Opus 5.5 $0.00008 $0.00644
Sonnet 5.5 $0.00004 $0.00322
Haiku 4.5 $0.00002 $0.00161

Measured 24d ago against content hash fb6e196d1114, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

formalize-intent 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 24d 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.

.agents/skills/formalize-intent/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Before executing this skill, read .agentic-mbse/claude.md in Claude Code or .agentic-mbse/codex.md in Codex. Resolve supporting paths from this skill’s installed directory; keep generated outputs in the project or a temporary directory. Read referenced skills from .agents/skills/<name>/SKILL.md when their guidance is needed.

Formalize Intent Command

Purpose: EXTRACT goals (G-XXX) and analysis questions (AQ-XXX) from raw intent documents, turning project prose into the structured entries that drive all downstream modeling work. Input: Documents in modeling_project/intent/ + existing modeling_project/OVERVIEW.md Output: Updated modeling_project/OVERVIEW.md (Goals Registry and Analysis Questions tables)

This is the bridge between "why are we doing this project?" and "what must the models do?" Goals and questions formalized here become the demand signal that /spec-model reads when scoping work items. Every G-XXX eventually drives modeling requirements (MR-XXX in specs, PR-XXX in project rules). Every AQ-XXX implies structural requirements on the models — if the models can't answer the question, they're incomplete.

Can be triggered by /onboard during initial setup or run standalone when new intent documents are added.

When invoked without arguments, scan modeling_project/intent/ for documents and proceed.

Skills Referenced

  • project-structure: 4-directory model, file organization. Consult when understanding where formalized output goes and how it connects to downstream artifacts.

Process

1. Read Intent and Existing State

If the user pointed to specific documents or provided intent directly in conversation, use that as the input. Otherwise, scan all documents in modeling_project/intent/ — these are user-authored prose (project charters, stakeholder notes, mission statements, meeting summaries). Use Explore agents to process multiple documents in parallel for efficiency.

Read modeling_project/OVERVIEW.md to see what's already formalized. For incremental runs, the existing Goals Registry and Analysis Questions tables show what's been extracted before — propose only new entries, not duplicates.

Read the full file on GitHub · 102 lines

Changes

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.

  1. 24d ago Changed · +4 lines fb6e196d1114
  2. 1mo ago First seen · 98 lines · 19 tokens per session scan A c20459934b58

Subscribe to this mod's changes

formalize-intent is a skill published in the GitHub repository 1cFE/fusion-tea (5 stars, last pushed 24d ago), licensed MIT. It adds 19 tokens to every session and 1,611 once invoked, about $0.0001 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 2026-09-29.

DocumentsPlanning
Related

formalize-intent compared with skills from other repositories

formalize-intent next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
formalize-intent1cFE/fusion-teaSkill524d agoMITA19Claude Code
orbit-notionnexu-io/open-designSkill106kyesterdayApache-2.0A117Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill35k2d agoApache-2.0A123Claude Code
baoyu-youtube-transcriptJimLiu/baoyu-skillsSkill27k4d agoMITA107Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skillsSkill49kyesterdayMITA48Claude Code
legal-holdanthropics/claude-for-legalSkill9.9k3d agoApache-2.0A68Claude Code
ppt-reviewOrkas-AI/OrkasSkill9.0kyesterdayMITA2Claude Code, Codex