agentmods.dev

mcp-gs-robot: Instructions file for Claude Code

CLAUDE.md

mcp-gs-robot CLAUDE.md is an instructions file for Claude Code from cfrs2005/mcp-gs-robot. It costs 1,746 tokens per session, scanned A, original, MIT.

Project-specific instructions for developing mcp-gs-robot, including its code layout, commands, conventions, and process for adding tools.

In plain words
What is it for?
Use them when editing the robot project's Python services, Vue frontend, APIs, MCP tools, or tests.
Why use it?
They give a coding agent the project context needed to make changes consistently and run the expected checks.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is cfrs2005/mcp-gs-robot's own configuration. It tells Claude Code how to work on mcp-gs-robot 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 mcp-gs-robot configures →

not rated 4repo +1 changed today A scan 1,746 tokens original MIT
View source ↗ cfrs2005/mcp-gs-robot
Reuse

Borrowing it

Nothing to install: this file belongs to cfrs2005/mcp-gs-robot. 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/cfrs2005/mcp-gs-robot/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/cfrs2005/mcp-gs-robot

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 mcp-gs-robot CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cfrs2005/mcp-gs-robot/claude-md/github.svg)](https://agentmods.dev/instructions/cfrs2005/mcp-gs-robot/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cfrs2005/mcp-gs-robot/claude-md"><img src="https://agentmods.dev/badge/instructions/cfrs2005/mcp-gs-robot/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.

agentmods 80×15 button for mcp-gs-robot CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cfrs2005/mcp-gs-robot/claude-md"><img src="https://agentmods.dev/badge/instructions/cfrs2005/mcp-gs-robot/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,746 This file is loaded in full into every session.
When invoked 1,746 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01746 $0.01746
Opus 5.5 $0.00698 $0.00698
Sonnet 5.5 $0.00349 $0.00349
Haiku 4.5 $0.00175 $0.00175

Measured today against content hash 990da8312cf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-30, from the pricing page.

Security

Grade A, and why

mcp-gs-robot 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 today.

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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-gs-robot · AI coding guide

Unofficial open-source software for personal research; not affiliated with, endorsed by, or supported by Gausium. Use at your own risk.

Layout

  • docs/ARCHITECTURE_V3.md: authoritative V3 contract for names, input shapes, entry points, and environment variables. Update it before changing the contract.
  • src/gs_openapi/v3/: typed V3 OpenAPI client and reference tables.
  • src/gs_openapi/tools/registry.py: single source of truth for all MCP, Agent, and REST tools; v3_tools.py, workflow_tools.py and knowledge_tools.py (lookup_error_code, remember) register handlers. ToolSpec.local=True marks tools that need no upstream client.
  • src/gs_openapi/mcp/ and src/gs_openapi/main.py: stdio MCP server and optional legacy tools.
  • src/gs_openapi/agent/: Saodi (扫地僧) agent, providers, sessions and CLI. soul.md (English; reply in the user's language) is the identity/safety layer; prompts.py builds the system prompt Soul → Knowledge → Memory (experience.md, then local memory.md) → $SAODI_CONTEXT_DIR/*.md. error-codes.md is not resident; the agent calls lookup_error_code.
  • src/gs_openapi/server/: FastAPI REST/SSE app and H5 static assets.
  • src/gs_openapi/store/: stdlib sqlite3 persistence at $SAODI_DATA_DIR/saodi.sqlite (default ~/.saodi/; db.py MIGRATIONS adds later columns idempotently): agent sessions (messages, errors and confirmations for replaying confirm cards), the tool-call log (recorded once in registry.invoke via a call observer) and error threads; saodi errors reads it. memory.py owns the private local memory $SAODI_DATA_DIR/memory.md (one - [YYYY-MM-DD] lesson per line, de-duplicated, credential-looking text refused).
  • h5/: Vue/Vite H5 frontend, builds into src/gs_openapi/server/static/.
    • h5/src/shared/tokens.css: design tokens (color, radius, shadow, type, spacing) and the Vant --van-* overrides; components use only these variables. shared/mark.svg is the Saodi AI robot-head mark (favicon, header, avatar); shared/robotModels.ts maps modelTypeCode (exact, then displayName/code keywords) to remote product images, never bundled; shared/reports.ts / format.ts hold report KPIs, per-day area and number/time formatting.
    • h5/src/shared/markdown.ts: renderSegments splits model text into DOMPurify-sanitized markdown runs and special fences (html → sandboxed HtmlPreview, mermaid → components/ui/MermaidView.vue), each with closed so unfinished fences show source while streaming. mermaid is the only diagram dependency and is loaded by dynamic import (separate chunks, never in the first-screen bundle); its SVG is re-sanitized (svg profile) and parse errors fall back to the source.
    • h5/src/components/cards/registry.ts: the single tool name → result card table (robot status, task reports, map images) used by ToolGroup for both live SSE and replayed history; results cut by the server carry _truncated (see fit_tool_output in agent/core.py, ARCHITECTURE_V3 §4) and the card says how many rows it shows. components/ui/ holds the shared pieces (robot image, battery, status pill, KPI tiles, hand-drawn SVG bar chart, map thumbnail, card shell); components/chat/ holds the chat header, composer, welcome home, dangerous-tool pipeline card, rule-based follow-ups and timeline.ts (event/transcript → reply parts).
    • h5/src/components/cards/LocateCard.vue: robot detail "Current location": the current map PNG with the robot (pulse + heading arrow) and map points / chargers overlaid in percent coordinates (left = x / gridWidth, top = (gridHeight - y) / gridHeight; angle in degrees, 0 = +x, CCW; canvas mapInfo wins). Read-only data: status, map canvas, map resources, and list_charging_positions through the generic POST /api/v1/tools/{name} (callTool in api/client.ts accepts read-only names only).
    • h5/src/api/fleet.ts: the fleet in one place: 60 s caches of list_robots (model lookup by SN) and of list_robots + live batch status (loadFleetStatus); fleetState() is the only online / offline / unreachable definition and fleetSummary() the only counter, used by both the chat home overview and the robot list. api/settings.ts is the API base/key store.
  • skills/gs-robot/: reusable Agent Skill and the single source of Saodi's Knowledge/Memory (packed into the wheel as gs_openapi/_skills/gs-robot via hatch force-include); references/experience.md is open-source call experience — never write SNs, traceIds, accounts, secrets or customer/site names there; docs/apis.md: V3 endpoint index with links to the official documentation.
  • docs/AGENT_SETUP_PROMPT.md: copy-paste setup prompt for coding agents (English + Chinese; also embedded in the READMEs).
  • README.md (English, primary) / README_CN.md (Chinese mirror): keep their sections aligned.
  • tests/: offline unit/integration tests with mock HTTP transport.

Read the full file on GitHub · 55 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. today Changed · +11 lines · +1,087 tokens per session 990da8312cf7
  2. yesterday First seen · 44 lines · 659 tokens per session scan A c24f50bb52fa

Subscribe to this mod's changes

mcp-gs-robot CLAUDE.md is an instructions file published in the GitHub repository cfrs2005/mcp-gs-robot (4 stars, last pushed yesterday), licensed MIT. It adds 1,746 tokens to every session, about $0.0070 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.

Building agents
Related

Other instructions, from other repositories

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 · 9,406 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 6,985 tokens

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 oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,009 tokens