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 musterhq/muster --skill muster-frappe-orchestratorgit clone --depth 1 https://github.com/musterhq/musterWrote 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/musterhq/muster/muster-frappe-orchestrator)<a href="https://agentmods.dev/skills/musterhq/muster/muster-frappe-orchestrator"><img src="https://agentmods.dev/badge/skills/musterhq/muster/muster-frappe-orchestrator/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/musterhq/muster/muster-frappe-orchestrator"><img src="https://agentmods.dev/badge/skills/musterhq/muster/muster-frappe-orchestrator.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 | $0.00066 | $0.00603 |
| Opus 5 | $0.00033 | $0.00302 |
| Sonnet 5 | $0.00013 | $0.00121 |
| Haiku 4.5 | $0.00007 | $0.00060 |
Grade A, and why
muster-frappe-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 11d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Muster Frappe Orchestrator
Build a native AI operating layer for Frappe, not a chat wrapper. Keep decisions, execution, approvals, evidence, and recovery visible inside the product.
Start With Reconnaissance
- Read repository instructions and inspect the dirty worktree before editing.
- Locate the target bench, site, Frappe version, installed apps, ports, process manager, and deployment boundaries.
- Map existing Muster core, gateway, OAuth, RBAC, workflow, channel, and Frappe capability code.
- Create an acceptance matrix covering desktop, mobile, permissions, failure recovery, observability, and evidence.
- Record assumptions and irreversible choices as ADRs before implementation.
For Frappe implementation, also load the relevant installed frappe-agent skills. Use the five specialist Muster skills for bounded sections of work.
Architecture Contract
Separate four planes:
- Control plane: tenants, identities, grants, policies, agents, workflow definitions, approvals, budgets, and credentials.
- Execution plane: durable runs, hierarchical tasks, leases, retries, cancellation, idempotency, tool calls, and artifacts.
- Experience plane: Desk/mobile workspaces, sidecar activity, mission control, previews, diffs, approvals, and undo.
- Evidence plane: immutable events, permission decisions, snapshots, test results, screenshots, traces, and release manifests.
Frappe is the system of record for business metadata and user-visible automation state. Muster is the execution engine. Communicate through versioned commands and events; do not couple the systems through ad hoc API calls.
Delegate Safely
When parallel work is authorized, assign non-overlapping ownership:
$muster-frappe-metadata: DocTypes and customization change sets.$muster-frappe-ui: native Frappe v16 desktop/mobile experience.$muster-frappe-workflows: agent graphs and durable execution.$muster-frappe-security: tenant isolation, OAuth, RBAC, and adversarial tests.$muster-frappe-release: benches, data, browser QA, evidence, and presentation.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 46 lines · 66 tokens per session scan A bdb368e164f6
muster-frappe-orchestrator is a skill published in the GitHub repository musterhq/muster (11 stars, last pushed 6d ago), licensed MIT. It adds 66 tokens to every session and 603 once invoked, about $0.0003 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.
Other skills, from other repositories
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
agency-change-management-consultant
Expert change management specialist using ADKAR, Kotter, and Prosci frameworks to guide organizations through technology implementations, restructuring, culture transformation, and M&A integration — managing resistance, building adoption, and ensuring changes stick long after go-live.
agency-hospitality-guest-services
Comprehensive hospitality guest services specialist for hotels, resorts, restaurants, and event venues — covering reservations, check-in/check-out, concierge services, guest complaint resolution, loyalty program management, and post-stay follow-up to deliver exceptional guest experiences that drive loyalty and revenue.
agency-it-service-manager
Expert IT service management specialist using ITIL 4 framework for service catalog design, incident and problem management, change control, SLA governance, CMDB maintenance, and continual service improvement — ensuring IT delivers reliable, measurable business value across any organization size.
agency-coach
Expert sales coaching specialist focused on rep development, pipeline review facilitation, call coaching, deal strategy, and forecast accuracy. Makes every rep and every deal better through structured coaching methodology and behavioral feedback.
agency-customer-success-manager
Strategic customer success specialist for onboarding, health scoring, QBR facilitation, churn prevention, expansion identification, and renewal management — driving net revenue retention by turning customers into long-term partners who achieve measurable outcomes.