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 skills add Frihet-io/frihet-mcp --skill frihet-workspacegit clone --depth 1 https://github.com/Frihet-io/frihet-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/skills/frihet-io/frihet-mcp/frihet-workspace)<a href="https://agentmods.dev/skills/frihet-io/frihet-mcp/frihet-workspace"><img src="https://agentmods.dev/badge/skills/frihet-io/frihet-mcp/frihet-workspace/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.
<a href="https://agentmods.dev/skills/frihet-io/frihet-mcp/frihet-workspace"><img src="https://agentmods.dev/badge/skills/frihet-io/frihet-mcp/frihet-workspace.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00095 | $0.01771 |
| Opus 5.5 | $0.00038 | $0.00708 |
| Sonnet 5.5 | $0.00019 | $0.00354 |
| Haiku 4.5 | $0.00010 | $0.00177 |
Grade A, and why
frihet-workspace 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frihet Workspace & Catalogue (frihet-workspace)
Respond in the user's language (English or Spanish). Use the connected Frihet MCP server as the single source of truth for workspace records.
Supported tools in this workflow
- Workspace orientation (read-only):
get_business_context - Product & service catalogue (read-only):
list_products,get_product - Product & service catalogue (write, requires
confirm: true):create_product,update_product - Cross-workspace read helpers (when a broader overview is requested):
list_invoices,list_quotes,list_expenses,list_clients,list_vendors
1. Capability orientation vs. workspace data inspection
Always distinguish a generic capability question from an authenticated workspace query:
A. Generic capability & welcome questions ("What can Frihet do?", "How do I use this plugin?", "¿Qué puede hacer Frihet?")
- Do NOT call
get_business_contextor any other MCP tool. A generic question about plugin capabilities, setup, or limits must never read private workspace records. - Answer directly by summarizing the four guided workflows and offering ready-to-use prompts:
- Workspace & Catalogue (
frihet-workspace): "Give me an overview of my business this month." / "Show me my active products and services." - Invoices & Quotes (
invoices-and-quotes): "Show me my draft invoices." / "Prepare an invoice draft for Acme SL." - Expenses & Vendors (
expenses-and-vendors): "List my expenses from this month." / "Record an office supplies expense." - Clients & CRM (
clients-crm): "List my clients and show recent CRM activity." / "Show notes for client Acme SL."
- Workspace & Catalogue (
- State the operational boundary briefly: read tools run only when you ask to inspect workspace records; write tools require explicit authorization (
confirm: true) and only create or update internal records and drafts.
B. Workspace overview requests ("Give me an overview of my business this month", "Give me my current Frihet business context overview", "Check my workspace plan usage and defaults")
- When the user explicitly asks to inspect their connected business, monthly summary, plan usage, or workspace defaults (or asks during
onboardingSkillsetup to verify their connected workspace):- Call
get_business_context(takes no arguments) to retrievebusiness,defaults,plan,currentMonth,recentActivity, andtopClients. - Present a concise, factual summary of the connected workspace:
- Workspace & defaults: business name and configured defaults (
defaults) when present. - Current month & plan usage: current-month totals (
currentMonth) and plan usage (plan). - Recent activity & top clients: highlight recent items from
recentActivityandtopClientswithout inventing fields omitted by the reviewed DTO.
- Workspace & defaults: business name and configured defaults (
- Do not call additional
list_*tools unless the user asks to drill into a specific area.
- Call
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 · 76 lines · 95 tokens per session scan A b43bed737b57
frihet-workspace is a skill published in the GitHub repository Frihet-io/frihet-mcp (12 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 1,771 once invoked, about $0.0004 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 2026-10-28.
Other skills, from other repositories
repo-defining-workflows
Workflow pattern standards for creating multi-agent orchestrations including two-key frontmatter with the goal, termination, inputs and outputs contract in body sections, execution phases (sequential/parallel/conditional), agent coordination patterns, and success criteria. Essential for defining reusable, validated…
plan-creating-project-plans
Project planning standards for authorized plans/ artifacts, including lifecycle naming, fixed mature core, bootcamp-graduate readability, alternatives and prior art, Gherkin criteria, granular delivery checklists, and evidence-first grilling.
agent-developing-agents
AI agent development standards including frontmatter structure, naming conventions, tool access patterns, model selection, and reference documentation structure.
plan-grooming-idea-briefs
Invocable entry point for the plan-ideas-grooming workflow: sweeps plans/ideas/ across repos into a deduplicated, Eisenhower-quadrant, correctly resident set of two-pagers, with residency rules, classification rubrics, fail-safe relocation, and a termination audit.
repo-maintaining-task-lists
The task-list obligation every agent carries — open the harness's native task list before any task, conversational ones included, and keep it in sync with actual progress. Auto-loads whenever work is about to begin.
repo-propagating-rules
Run the rules-propagation workflow whenever a repository rule is being created, updated, superseded, or deleted. TRIGGERS on "add rule", "new rule", "update the rule", "change the convention", "adjust the rule", "delete that rule", "make it a rule that…", "from now on we should…", "we should always/never…", or any…