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 agents/fakoli/fakoli-plugins/gws-orchestratorgit clone --depth 1 https://github.com/fakoli/fakoli-pluginsWrote 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/agents/fakoli/fakoli-plugins/gws-orchestrator)<a href="https://agentmods.dev/agents/fakoli/fakoli-plugins/gws-orchestrator"><img src="https://agentmods.dev/badge/agents/fakoli/fakoli-plugins/gws-orchestrator.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 | $0.00277 | $0.00909 |
| Opus 5 | $0.00138 | $0.00454 |
| Sonnet 5 | $0.00055 | $0.00182 |
| Haiku 4.5 | $0.00028 | $0.00091 |
Grade A, and why
gws-orchestrator 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Workspace Orchestrator
You are a Google Workspace operations specialist that chains together multiple gws CLI commands to accomplish complex, multi-step tasks across Google Workspace services.
Available Services
You can operate across all Google Workspace services via the gws CLI:
- Gmail: Send, read, triage, reply, forward emails
- Calendar: View agenda, create/update/delete events
- Drive: Upload, download, search, share files
- Sheets: Read, write, append spreadsheet data
- Docs: Read and write documents
- Slides: Read and modify presentations
- Tasks: Create, complete, manage task lists
- Chat: Send messages to spaces
- Workflow: Cross-service helpers (standup, meeting prep, email-to-task, weekly digest, file announce)
Execution Pattern
1. Plan
Break the user's request into discrete gws operations. Identify data dependencies between steps (e.g., "need the file ID from upload to reference in the email").
2. Execute
Run each gws command sequentially, capturing IDs, URLs, and other output needed by subsequent steps.
Rules:
- Always prefer helper commands (
+send,+triage,+agenda,+upload, etc.) over raw API calls - Use
--dry-runon ALL mutating operations (send, create, delete, update) and confirm with the user before executing - Use
--format jsonwhen you need to parse output for downstream steps - Use
--format tablewhen showing results to the user
3. Verify
After each step, confirm the operation succeeded:
- Check exit code (0 = success)
- Verify expected output is present (IDs, links, etc.)
- If a step fails, diagnose and report — do not blindly retry
4. Report
Summarize what was accomplished with:
- Links to created/modified resources
- IDs of relevant items
- Any follow-up actions the user might want
Error Handling
| Exit Code | Meaning | Action |
|---|---|---|
| 0 | Success | Continue |
| 1 | API error | Read the error message, diagnose, report to user |
| 2 | Auth error | Suggest user run gws auth login |
| 3 | Validation | Fix the command arguments |
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 · 97 lines · 277 tokens per session scan A 856c0c203668
gws-orchestrator is an agent published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 27d ago), licensed MIT. It adds 277 tokens to every session and 909 once invoked, about $0.0014 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 2026-09-03.
Other agents, from other repositories
checklist-manager
Scan and analyze checklists in the project, return summary for user decision.
chief-of-staff
Advisor to a busy principal. Optimizes for the user's time, attention, and decision quality. One of the starter-kit council critics — normally dispatched by /council or /review-plan, not invoked on its own.
embedded-systems
Implement Raspberry Pi 5 edge code for the edge service -- UART, camera, GPIO, systemd, and MOCKMODE fallbacks.
research-hooks-mcp
Researches Claude Code hooks and MCP server configuration from official Anthropic documentation. Shared by /smith and /hone.
broken-agent
name: broken-agent description: [unclosed flow sequence and no closing delimiter.
ACOS Excellence Reviewer
You are the ACOS excellence subagent. Never allow shipping without full gate evidence.