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/orieg/gws-connector/agents-mdgit clone --depth 1 https://github.com/orieg/gws-connectorWrote 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/orieg/gws-connector/agents-md)<a href="https://agentmods.dev/instructions/orieg/gws-connector/agents-md"><img src="https://agentmods.dev/badge/instructions/orieg/gws-connector/agents-md.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 | $0.00922 | $0.00922 |
| Opus 5 | $0.00461 | $0.00461 |
| Sonnet 5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
gws-connector AGENTS.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 4d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents (and humans) working in this repository. This
follows the agents.md convention and complements
CONTRIBUTING.md.
Note:
CONTEXT.mdis different — it is the runtime behavioral guide loaded by MCP clients that describes how to use thegws.*tools. This file describes how to develop the project.
What this project is
A multi-account Google Workspace MCP server in Go. It exposes Gmail, Calendar, Drive, Sheets, and Docs as MCP tools with per-account OAuth and label/email/domain routing. It ships as a Claude Code plugin, a Gemini CLI extension, and a plain MCP server over stdio.
Build, test, lint
make build # build ./bin/gws-mcp
make test # go test with -race (authoritative check)
make lint # go vet
gofmt -w <files> # ALWAYS gofmt Go files you edit
Always run make test and make lint before finishing a change. CI additionally
runs govulncheck; keep dependencies patched.
Codebase map
| Path | Responsibility |
|---|---|
cmd/gws-mcp/ |
Entrypoint; env vars; starts MCP server on stdio |
internal/server/server.go |
Tool registration & dispatch — start here to add/change a tool |
internal/services/ |
Gmail, Calendar, Drive, Sheets, Docs API handlers |
internal/auth/ |
OAuth flows, token store (OS keychain + file fallback), client factory |
internal/accounts/ |
Account registry (JSON) and routing resolution |
skills/ |
Slash-command workflows (Claude Code + Gemini CLI) |
hooks/, agents/ |
Claude Code session hooks and workspace-context agent |
docs/ |
GitHub Pages landing page + privacy policy |
Conventions
- Tool naming:
s.toolName("gws", "<group>", "<verb>"). The--use-dot-namesflag switches betweengws.mail.searchandgws_mail_search— never hardcode a separator. - Tool annotations (required on every new tool):
- Read-only (search/read/list/get):
mcp.WithReadOnlyHintAnnotation(true) - Overwrites or deletes data (remove,
sheets.write_range,docs.replace_text):mcp.WithDestructiveHintAnnotation(true) - Additive writes (create/insert draft/event/label/doc): omit both hints.
- Read-only (search/read/list/get):
- Account parameter: every service tool takes an optional
accountparam (accountParamin eachregister*Tools). Preserve this. - Security: never log tokens or put them in error messages; state files are
0600, dirs0700; validate params used in Google API queries. - Commits: Conventional Commits (
feat(scope): …,fix(scope): …). Atomic. - Docs stay in sync: adding/changing a tool means updating the README tool
table and, if it changes runtime behavior,
CONTEXT.md.
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.
- 4d ago First seen · 79 lines · 922 tokens per session scan A 88d2b3fd2add
gws-connector AGENTS.md is an instructions file published in the GitHub repository orieg/gws-connector (1 stars, last pushed 2d ago), licensed MIT. It adds 922 tokens to every session, about $0.0046 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.
Other instructions, from other repositories
notfair-plugin AGENTS.md
AGENTS.md instructions for nowork-studio/notfair-plugin, covering notfair — skill resolver for ai agents, how to use this file, seo, paid ads and analytics.
notfair-plugin CLAUDE.md
Claude Code instructions for nowork-studio/notfair-plugin, covering engineering execution standard, agent entry points (single sources of truth), working style: brutal honesty, relentless quality, repository purpose and critical: this ships to users.
domscribe CLAUDE.md
Instructions for patchorbit/domscribe, covering claude.md, what is domscribe?, how to work on this codebase, commands and install dependencies (pnpm, not npm).
writing-skills AGENTS.md
AGENTS.md instructions for surendranb/writing-skills, covering agents.md — writing-skills, what this is, layout, the skill anatomy contract (enforced by ci) and working here.
logic-lens GEMINI.md
Instructions for hyhmrright/logic-lens, covering logic-lens — developer guide (gemini cli), invoking skills, installation, project layout and key conventions.
flutter-slipstream CLAUDE.md
Instructions for devoncarew/flutter-slipstream, covering flutter-slipstream, feature: flutter ui agent, feature: package api retrieval, feature: package safety skill and supported coding agents.