What is fusion-tea CLAUDE.md?

A project-specific instruction file for Claude Code, an AI coding assistant. It explains fusion-tea, its domain concepts, investigation approach, and project structure.

Learning the project structure, understanding domain terms, investigating unfamiliar code, and guiding new work.

It gives the assistant background and a prescribed way to investigate the code before making changes.

How 1cFE/fusion-tea configures Claude Code

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/CLAUDE.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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/1cfe/fusion-tea/claude-md/github.svg)](https://agentmods.dev/instructions/1cfe/fusion-tea/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/1cfe/fusion-tea/claude-md"><img src="https://agentmods.dev/badge/instructions/1cfe/fusion-tea/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/1cfe/fusion-tea/claude-md"><img src="https://agentmods.dev/badge/instructions/1cfe/fusion-tea/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,741 This file is loaded in full into every session.

When invoked 5,741 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.05741	$0.05741
Opus 5.5	$0.02296	$0.02296
Sonnet 5.5	$0.01148	$0.01148
Haiku 4.5	$0.00574	$0.00574

Measured 23d ago against content hash 34a6278eabc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fusion-tea 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 23d 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.

CLAUDE.md · 366 lines

How it starts

The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Design-choice preservation

Before planning or changing model equations, parameter roles, equipment/capacity bindings or demand-based costs, read MR-7 and apply its evidence and review checks through modeling_project/MODELING_PROCESS.md. Goal agents carry the same requirement through work/orchestration/GOAL_RUNBOOK.md. Existing sizing code and passing depth scores do not authorize a fixed design-variable assignment. This pointer is shared by Claude and Codex through AGENTS.md; the requirement itself has one authoritative home.

Goal layer in this repository

run-goal, narrate-goal, work/orchestration/GOAL_RUNBOOK.md and its templates are installed by agentic-mbse and name the research, integration and study procedures generally. Here they are:

Research: the installed research-acquire skill drives search and triage; uv run agentic-mbse research open|log|register|close keeps the run and writes the registry, and retire/verify maintain it. Form request files at knowledge/research/requests/REQ-*.json. Operator guide: docs/research-seam.md in the installed toolkit's docs directory. The ARIES-CS guard scripts/holdout_guard.py is the registry's hold-out hook (pyproject.toml [tool.agentic-mbse.research]); a hit is adjudicated only through PROTOCOL §6, outside the seam, and the guard is a term scan that misses barred content which never names a barred term. Every researcher applies the clean-room screen (knowledge/holdout/aries-cs/PROTOCOL.md) before any fetch. Zotero ingest registers through the same package. Registered locations are cited under MR-4.
Integration: scripts/integrate.py (.project/adr/0009-integration-is-a-fixed-point-proof.md); guide docs/integration_seam_operator_guide.md.
Studies: .claude/skills/run-study/runbook.md and modeling_project/STUDY_POLICY.md. Discovery logs are exploration/<pkg>/studies/DISCOVERY_LOG.md; tests/study/test_records.py::test_findings_join_the_discovery_log checks the join.
Decision records: this repository's goal-layer ADRs stay in .project/adr/ and govern it; installed targets use agentic-mbse's dated snapshot.
Launcher: in the Codex test worktree use .codex-test/run (AGENTS.md); otherwise uv run.

Read the full file on GitHub · 366 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.

23d ago Changed · +9 lines · +436 tokens per session 34a6278eabc6
24d ago Changed · +10 lines · +330 tokens per session 2f8cf739934e
27d ago Changed · +8 lines · +297 tokens per session 65320c5f737c
1mo ago Changed · +4 lines · +132 tokens per session f924aade4f89
2mo ago First seen · 335 lines · 4,546 tokens per session scan A 7d825e073875

Subscribe to this mod's changes

fusion-tea CLAUDE.md is an instructions file published in the GitHub repository 1cFE/fusion-tea (5 stars, last pushed 24d ago), licensed MIT. It adds 5,741 tokens to every session, about $0.0230 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 2026-08-31.

fusion-tea CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fusion-tea CLAUDE.md1cFE/fusion-tea	Instructions file	5	24d ago	MIT	A	5,741	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

fusion-tea: Instructions file for Claude Code