What is VectorClaw copilot-instructions.md?

Project-specific coding instructions for VectorClaw, a Python MCP server that controls Anki Vector robots. They define which SDK documentation to check, along with project testing, safety, and runtime rules.

Use them when adding or modifying Vector robot tools, reviewing SDK calls, locating project documentation, or working in the source and tests of the repository.

They reduce mistakes when changing robot-control code, especially incorrect SDK property names or method signatures. They also keep contributions focused and consistent with the repository’s documented constraints.

VectorClaw copilot-instructions.md — Instructions file by danmartinez78

Install

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.

agentmods

npx agentmods add instructions/danmartinez78/vectorclaw/copilot-instructions

Clone the repo

git clone --depth 1 https://github.com/danmartinez78/VectorClaw

Made for: GitHub Copilot.

Per session 418 This file is loaded in full into every session.

When invoked 418 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00418	$0.00418
Opus 5	$0.00209	$0.00209
Sonnet 5	$0.00084	$0.00084
Haiku 4.5	$0.00042	$0.00042

Measured 2d ago against content hash 7336e4dc22c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

VectorClaw copilot-instructions.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 2d 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.

.github/copilot-instructions.md · 56 lines

What it actually says

Copilot Instructions for VectorClaw

Project Context

This repository provides an MCP server that controls Anki Vector robots.
Python package source lives under src/vectorclaw_mcp.
Tests live under tests/.

⚠️ CRITICAL: SDK Surface Documentation

Before implementing or modifying ANY tool that interacts with the SDK, you MUST:

Read the authoritative SDK surface reference: docs/VECTOR_SDK_REFERENCE.md
Verify all property names, method signatures, and behavior against this doc
Do NOT assume field names or behavior — check the reference

During code review, verify:

All SDK property names match the reference doc exactly
All method calls use correct signatures from the reference doc
All behavior expectations align with SDK documentation

Common mistakes to avoid:

is_carrying_object → wrong (use is_carrying_block)
is_on_charger_platform → wrong (use is_on_charger)
Assuming perception tools work without enabling vision modes
Assuming found_object in proximity sensor means "distance changed"

When in doubt, search the SDK surface doc first.

Contribution Defaults

Keep changes minimal and task-focused.
Preserve existing public tool names and API behavior unless explicitly requested.
Prefer small pure functions where possible.
Add or update tests for changed behavior.

Safety and Runtime Constraints

Do not execute robot movement by default in tests.
Keep hardware-dependent logic isolated behind interfaces that can be mocked.
Avoid adding blocking operations to MCP tool handlers.

Development Workflow

Use the devcontainer setup for consistency.
Run pytest -q before finalizing.
If packaging or dependency metadata changes, validate with python -m build.

Documentation

When behavior changes, update docs in:

README.md for user-facing usage
docs/SETUP.md for setup/runtime details
ROADMAP.md only for planning-level updates

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.

2d ago First seen · 56 lines · 418 tokens per session scan A 7336e4dc22c8

Subscribe to this mod's changes

VectorClaw copilot-instructions.md is an instructions file published in the GitHub repository danmartinez78/VectorClaw (20 stars, last pushed 2mo ago), licensed MIT. It adds 418 tokens to every session, about $0.0021 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 2026-08-30.

Data and AI Testing Writing and docs

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 · 5,182 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

VectorClaw copilot-instructions.md