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-securitygit 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-security)<a href="https://agentmods.dev/skills/musterhq/muster/muster-frappe-security"><img src="https://agentmods.dev/badge/skills/musterhq/muster/muster-frappe-security/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-security"><img src="https://agentmods.dev/badge/skills/musterhq/muster/muster-frappe-security.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 | $0.00064 | $0.00694 |
| Opus 5 | $0.00032 | $0.00347 |
| Sonnet 5 | $0.00013 | $0.00139 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
muster-frappe-security 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Muster Frappe Security
Make identity and authorization continuous: authenticate the actor, bind the tenant/site, resolve the effective Frappe user, authorize the exact operation, constrain delegated agents, and audit the outcome.
Trust Model
- A tenant, Frappe site, Muster gateway, channel identity, and Frappe user are separate principals with explicit bindings.
- OAuth proves an identity and scopes a token; it does not replace Frappe role and document permission checks.
- Child agents receive attenuated capabilities, never an ambient copy of the parent session.
- Background and Telegram actions run as a recorded user or service principal with bounded roles, expiry, and revocation.
- Credentials are encrypted at rest, redacted everywhere, rotated, and never placed in workflow JSON, browser state, events, or artifacts.
Review Workflow
- Draw trust boundaries and data flows for browser, Frappe, Muster gateway, workers, model providers, channels, and storage.
- Enumerate assets, actors, entry points, escalation paths, and cross-tenant identifiers.
- Define deny-by-default policy and the exact Frappe permission API used at plan, approval, execution, and readback time.
- Bind approvals to immutable action hashes, identity, tenant, scope, and expiry. Revalidate after any change.
- Keep high-risk operations behind fresh approval and server-side enforcement.
- Produce automated positive and negative matrices plus auditable evidence.
Required Attacks
Test horizontal and vertical privilege escalation, tenant/site confusion, forged OAuth state, token replay, revoked roles, field-level leakage, child-agent overreach, approval substitution, prompt/tool injection, webhook forgery, Telegram identity collision, ID enumeration, SSRF, stored XSS, unsafe print/template code, queue replay, log leakage, and denial-of-service limits.
Do not use generic pairing as proof of a Frappe identity. A streamlined channel onboarding flow may start from an authenticated Frappe session and a short-lived one-time link, but it must retain explicit consent, expiry, single use, device/channel confirmation, and revocation.
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 · 38 lines · 64 tokens per session scan A 0e17b443da75
muster-frappe-security is a skill published in the GitHub repository musterhq/muster (11 stars, last pushed 6d ago), licensed MIT. It adds 64 tokens to every session and 694 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.
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
efficient-execution
Reduce token waste and task completion time by choosing the simplest tool for each job.
task-planning
Match planning effort to task complexity. Check existing skills before inventing a new approach.
learning-capture
Log corrections, errors, and discoveries to orbital/LESSONS.md so future sessions avoid repeating mistakes.
process-capture
Capture successful multi-step workflows as reusable skills so future sessions can replay them.