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-releasegit 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-release)<a href="https://agentmods.dev/skills/musterhq/muster/muster-frappe-release"><img src="https://agentmods.dev/badge/skills/musterhq/muster/muster-frappe-release/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-release"><img src="https://agentmods.dev/badge/skills/musterhq/muster/muster-frappe-release.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 | $0.00726 |
| Opus 5 | $0.00033 | $0.00363 |
| Sonnet 5 | $0.00013 | $0.00145 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
muster-frappe-release 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Muster Frappe Release
Release through an isolated, reproducible Frappe bench and an artifact-backed quality gate. A polished demo is evidence of a verified system, not a substitute for tests.
Environment Workflow
- Load
frappe-agent:frappe-benchand inspect versions, installed apps, sites, ports, services, disk, backups, and dirty repositories. - Use a dedicated bench/site and unused ports for Muster. Do not modify customer benches unless explicitly scoped.
- Pin Frappe, ERPNext, Python, Node, app revisions, and dependency locks. Record commands without secrets.
- Validate clean install, migrate, restart, upgrade from the prior schema, backup/restore, and safe uninstall where supported.
- Publish health, version, migration, queue, scheduler, websocket, and gateway checks.
Data and Test Matrix
Seed deterministic but realistic companies, departments, users, roles, customers, suppliers, items, transactions, projects, tickets, HR records, custom DocTypes, metadata, agents, workflows, runs, approvals, and artifacts. Include sparse, malformed, high-volume, multilingual, long-text, attachment, and boundary data.
Run unit, schema, integration, permission, migration, queue/realtime, browser, narrow-mobile, accessibility, concurrency, load, soak, chaos, backup/restore, and security-negative suites. Preserve logs and results with timestamps, versions, hashes, and environment identity.
Each case writes one JSON result with schema_version, case_id, claim_id, environment_id, code and app revisions, site, actor and roles, tenant/company scope, fixture ids, start/end timestamps, expected outcome, actual outcome, status, side-effect assertions, artifact paths and hashes, and redacted diagnostics. A release manifest enumerates required cases and thresholds; missing, skipped, flaky, unhashed, or stale results fail the gate.
Set measurable thresholds before the run: zero authorization or tenant-isolation failures, zero lost/duplicated committed effects, zero unresolved high/critical security findings, all migration/restore cases passing, and agreed p95 UI/API/queue targets under the seeded load. Record lower-severity exceptions with owner and expiry.
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 · 39 lines · 66 tokens per session scan A 0cc8e4b8b203
muster-frappe-release 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 726 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
dogfood
Systematic exploratory QA testing of web applications — find bugs, capture evidence, and generate structured reports.
test-reporting
Run the Level 2 dummy agent integration test suite and produce a detailed HTML report with per-test input → outcome analysis.
auto-canary
A deployment health-check skill for testing whether a recently deployed or staging website is working. It runs build, end-to-end, and browser checks, then reports a pass, warning, or failure.
run-dashboard-e2e-local-changes
Run Playwright E2E (tests/e2e/) against the docker/ all-in-one harness so it reflects LOCAL code changes, not a stale cached image.
uat-testing
Run end-to-end User Acceptance Tests for Agent Brain features. Builds wheels, installs packages, starts a test server, runs tests, and reports results — all without permission prompts.
playwright-uitest
Generate Playwright UI tests and visual smoke reports for delivery POC frontends.