What is Charter CLAUDE.md?

Project instructions for Charter, a desktop development environment built with Electron, React, TypeScript, and Monaco.

Guiding work across Charter’s milestones, agent runtime, renderer, editor, acceptance tests, architecture decisions, and release requirements.

They define the required architecture, source documents, security boundaries, and completion criteria so implementation stays aligned with the product specification.

How longyunfeigu/Charter configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to longyunfeigu/Charter. 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/longyunfeigu/Charter/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/longyunfeigu/Charter

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/longyunfeigu/charter/claude-md.svg)](https://agentmods.dev/instructions/longyunfeigu/charter/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/longyunfeigu/charter/claude-md"><img src="https://agentmods.dev/badge/instructions/longyunfeigu/charter/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 827 This file is loaded in full into every session.

When invoked 827 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	$0.00827	$0.00827
Opus 5	$0.00413	$0.00413
Sonnet 5	$0.00165	$0.00165
Haiku 4.5	$0.00083	$0.00083

Measured 8d ago against content hash d44ce7b47128, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Charter 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 8d 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Pi-powered Agentic IDE

Mission

Build the complete V1.0 desktop product defined in docs/PRODUCT_ENGINEERING_SPEC.md. This is not a prototype. Do not stop after the Electron shell, editor, or read-only Pi integration. Completion requires all 12 milestones and all release gates.

Source of truth

docs/PRODUCT_ENGINEERING_SPEC.md
docs/UX_PIVOT_SPEC.md — shell/branding layer (ADR-0004): dual-form "Charter" supersedes spec §4 entry/branding; engine spec unchanged
docs/IMPLEMENTATION_BACKLOG.md
Acceptance tests and state-machine invariants
ADRs in docs/adr/ and docs/DECISIONS.md

When requirements conflict, acceptance criteria take precedence. Record interpretations in an ADR; do not silently remove scope.

Non-negotiable architecture

Electron + React + TypeScript + Monaco.
Pi runs outside the renderer in an agent utility/child process.
Only packages/agent-runtime-pi may import Pi packages.
UI/domain code depends on the product AgentRuntime and AgentEvent contracts.
Do not copy Pi source into this repository. Pin the SDK exactly.
Renderer: nodeIntegration=false, contextIsolation=true, sandbox=true.
No generic IPC bridge. Every channel has a versioned runtime schema.
Pi never gets unrestricted filesystem/shell access. All tools go through Tool Gateway and Permission Engine.
File changes use revision/hash checks, snapshots, atomic writes and conflict handling.
Agent completion means REVIEW_READY, never automatic ACCEPTED — except the user-opt-in Full mode (ADR-0012): system auto-accept after completion, with verification-failure/merge-conflict fallbacks to review and post-accept rollback.

Working protocol

Read the complete specification and backlog before coding.
Work milestone by milestone and dependency order.
Keep the application runnable after every task.
For each task: implement happy path, failure/cancel path, tests, logs, docs, and migration if needed.
Run npm run check and relevant tests before marking DONE.
Mark VERIFIED only after the milestone exit test passes.
Update docs/IMPLEMENTATION_STATUS.md after each meaningful change.
After adding or changing any user-visible feature: update README.md and README.zh-CN.md in the same change set, then sync the marketing site at ~/git/charter-site — edit public/index.html and public/zh/index.html in lockstep, follow that repo's CLAUDE.md brand rules (no internal names, no overstated status), commit and push main (Cloudflare Pages auto-deploys to https://charter-15n.pages.dev).
Add an ADR for dependency changes, architecture deviations, security tradeoffs or Pi patches.
Never use static fake UI in a completed feature. Mock Runtime is allowed only as a deterministic backend for tests/dev.
Never bypass an acceptance failure by weakening the test unless the specification is formally changed.

Read the full file on GitHub · 66 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.

8d ago First seen · 66 lines · 827 tokens per session scan A d44ce7b47128

Subscribe to this mod's changes

Charter CLAUDE.md is an instructions file published in the GitHub repository longyunfeigu/Charter (10 stars, last pushed 18d ago), licensed MIT. It adds 827 tokens to every session, about $0.0041 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 2026-08-31.

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

Charter: Instructions file for Claude Code