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.
npx agentmods add instructions/shigechika/gws-mcp/copilot-instructionsgit clone --depth 1 https://github.com/shigechika/gws-mcpWrote 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.
[](https://agentmods.dev/instructions/shigechika/gws-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/shigechika/gws-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/shigechika/gws-mcp/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02118 | $0.02118 |
| Opus 5 | $0.01059 | $0.01059 |
| Sonnet 5 | $0.00424 | $0.00424 |
| Haiku 4.5 | $0.00212 | $0.00212 |
Grade A, and why
gws-mcp 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository overview
gws is a Rust CLI for Google Workspace APIs. It dynamically generates its
command surface at runtime by parsing Google Discovery Service JSON documents
— it does not use generated crates like google-drive3. This repository
is shigechika/gws-mcp, a fork of googleworkspace/cli that keeps an
MCP (Model Context Protocol) server upstream removed. It stays close to
upstream on purpose: minimize divergence so future upstream merges stay
low-conflict.
Cargo workspace, two crates:
crates/google-workspace/— publishable library (Discovery models, HTTP client, path/URL/resource validators invalidate.rs)crates/google-workspace-cli/— thegwsbinary (arg parsing, executor, auth, helpers, and the fork-onlymcp_server.rs)
Full architecture, workspace layout, and helper-command conventions are in
AGENTS.md at the repo root — read it before reviewing changes to
executor.rs, validate.rs, or anything under helpers/.
Build & validate
cargo build # dev build, both crates
cargo test -p google-workspace # library unit tests
cargo test -p google-workspace-cli # CLI unit tests
cargo clippy --workspace -- -D warnings # exact command CI runs — not --all-targets
cargo fmt --check
A .rs/Cargo.* change without a .changeset/*.md file fails the Policy Check CI job. Changeset format:
---
"@googleworkspace/cli": patch
---
One-paragraph description of the fix.
What to focus review on in this repo
1. URL construction is a real attack surface — this CLI is driven by LLM/MCP agents
AGENTS.md → "Input Validation & URL Safety" defines the contract precisely.
Check every diff that builds a URL against it:
- Path segments: user input must go through
crate::validate::encode_path_segment(). Never format raw input into a path. - Query parameters: must go through reqwest's
.query()builder, NOT rawformat!("...?key={value}")string interpolation. A value containing&in a hand-formatted query string silently truncates/splits into extra parameters;+gets decoded server-side as a space. (This exact class of bug shipped once inhelpers/modelarmor.rsand was only caught in manual review, not by an earlier automated pass — flag anyformat!containing?or&next to a variable.) - Resource names (project IDs, space names, topic names) must go through
crate::validate::validate_resource_name()before being embedded anywhere. - If a diff touches
crate::validate::encode_path_segment,validate_resource_name, or any other function invalidate.rs: grep for every caller acrosscrates/(there are call sites scattered acrossexecutor.rs,discovery.rs, and multiple files underhelpers/— don't trust a fixed list, re-grep each time, since new helpers add new callers) and check each one still gets the behavior it relies on — these are shared, security-sensitive utilities, not single-use helpers. A change that's correct for the file it's in can still break a different caller with a different usage pattern (e.g. a path-segment encoder reused for a query value).
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.
- 5d ago First seen · 166 lines · 2,118 tokens per session scan A da2dc3616a87
gws-mcp copilot-instructions.md is an instructions file published in the GitHub repository shigechika/gws-mcp (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,118 tokens to every session, about $0.0106 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.