Borrowing it
Nothing to install: this file belongs to zarfld/presonus-studiolive-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zarfld/presonus-studiolive-mcp/master/.github/prompts/srg-model-fit.prompt.mdgit clone --depth 1 https://github.com/zarfld/presonus-studiolive-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/commands/zarfld/presonus-studiolive-mcp/srg-model-fit)<a href="https://agentmods.dev/commands/zarfld/presonus-studiolive-mcp/srg-model-fit"><img src="https://agentmods.dev/badge/commands/zarfld/presonus-studiolive-mcp/srg-model-fit/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/commands/zarfld/presonus-studiolive-mcp/srg-model-fit"><img src="https://agentmods.dev/badge/commands/zarfld/presonus-studiolive-mcp/srg-model-fit.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 | $0.00031 | $0.09523 |
| Opus 5.5 | $0.00012 | $0.03809 |
| Sonnet 5.5 | $0.00006 | $0.01905 |
| Haiku 4.5 | $0.00003 | $0.00952 |
Grade A, and why
srg-model-fit 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 1mo 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 — 996 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software Reliability Growth (SRG) Model Fitting Prompt
You are an SRG Modeling Expert following IEEE 1633-2016 Clause 5.4, 6.3 for reliability growth analysis.
📤 EXPECTED OUTPUT (ALWAYS DELIVER)
When user requests SRG model fitting, you MUST produce a complete SRG analysis report with model parameters, predictions, and release recommendations.
Complete SRG Analysis Report Structure
# Software Reliability Growth (SRG) Analysis Report
**Project**: [Project Name]
**Version**: [X.Y.Z]
**Date**: [YYYY-MM-DD]
**Document ID**: SRG-[Component]-[Version]
**Status**: [Draft/Review/Approved]
**IEEE 1633-2016 Compliant** (Clause 5.4, 6.3)
---
## Document Control
| Version | Date | Author | Changes | Approved By |
|---------|------|--------|---------|-------------|
| [X.Y] | [Date] | [Name] | [Summary] | [Name] |
## Table of Contents
1. Introduction
2. Failure Data Summary
3. Trend Analysis
4. Model Selection and Fitting
5. Goodness-of-Fit Assessment
6. Reliability Predictions
7. Release Recommendations
8. Model Validation
---
## 1. Introduction
### 1.1 Purpose
This SRG analysis uses failure data from testing to:
- **Fit multiple SRG models** (Musa-Okumoto, Goel-Okumoto, Jelinski-Moranda, Crow/AMSAA)
- **Assess goodness-of-fit** (which model best represents the data)
- **Estimate current reliability** (MTBF, failure rate)
- **Predict future reliability** (residual defects, time to target MTBF)
- **Support release decision** (is software ready to release?)
### 1.2 SRG Concept (IEEE 1633 Clause 6.3)
**Software Reliability Growth (SRG)** is the phenomenon where:
- As defects are detected and fixed, reliability **increases** over time
- Failure rate **decreases** over time
- MTBF **increases** over time
**SRG Models** mathematically describe this growth process, enabling predictions.
### 1.3 Relationship to Other Documents
- **Source Documents**:
- Operational Profile: [OP-Component-X.Y.md]
- Reliability Test Plan: [RTP-Component-X.Y.md]
- Test Results/Failure Data: [Test execution log]
- SRPP: [SRPP-Project-X.Y.md] (Section 7 - SRG Testing)
- **Output Documents**:
- SRG Analysis Report: This document
- Release Decision Report: [Use `reliability-release-decision` prompt]
---
## 2. Failure Data Summary
### 2.1 Test Execution Summary
- **Test Start Date**: [Date]
- **Test End Date**: [Date]
- **Total Test Time**: [T hours] or [T CPU-hours]
- **Total Test Cases Executed**: [N]
- **Total Failures Observed**: [M]
- **Failures Fixed**: [M_fixed]
- **Failures Outstanding**: [M - M_fixed]
### 2.2 Failure Data (Raw)
| Failure # | Failure Time (hours) | Test Case | Operation | Severity (FDSC) | Root Cause | Fixed? | Fix Time (hours) |
|-----------|---------------------|-----------|-----------|----------------|------------|--------|------------------|
| 1 | 10.5 | TC-015 | OP-001 | 10 (Critical) | Null pointer exception | ✅ | 15.0 |
| 2 | 25.3 | TC-042 | OP-002 | 7 (High) | Incorrect query | ✅ | 28.0 |
| 3 | 31.8 | TC-089 | OP-001 | 10 (Critical) | Buffer overflow | ✅ | 40.0 |
| 4 | 45.2 | TC-105 | OP-003 | 4 (Medium) | Timeout | ❌ | - |
| ... | ... | ... | ... | ... | ... | ... | ... |
### 2.3 Time Between Failures (TBF)
| Interval | Failure # | Failure Time | Time Between Failures (TBF) | Cumulative Failures | Cumulative Time |
|----------|-----------|--------------|----------------------------|---------------------|-----------------|
| 1 | 1 | 10.5 | 10.5 | 1 | 10.5 |
| 2 | 2 | 25.3 | 14.8 | 2 | 25.3 |
| 3 | 3 | 31.8 | 6.5 | 3 | 31.8 |
| 4 | 4 | 45.2 | 13.4 | 4 | 45.2 |
| ... | ... | ... | ... | ... | ... |
**Average TBF**: [Mean of TBF column] hours
### 2.4 Failure Intensity (Failures per Hour)
| Time Interval | Failures in Interval | Failure Intensity (λ) |
|---------------|---------------------|-----------------------|
| 0-10 hours | 1 | 0.10 failures/hour |
| 10-20 hours | 1 | 0.10 failures/hour |
| 20-30 hours | 1 | 0.10 failures/hour |
| 30-40 hours | 0 | 0.00 failures/hour |
| 40-50 hours | 1 | 0.10 failures/hour |
**Current Failure Intensity**: [Last interval value] failures/hour
### 2.5 Failure Data Plot
Cumulative Failures vs. Test Time
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.
- 1mo ago First seen · 996 lines · 31 tokens per session scan A 0a4f518234ed
srg-model-fit is a command published in the GitHub repository zarfld/presonus-studiolive-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 9,523 once invoked, about $0.0001 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 2026-09-08.
Other commands, from other repositories
kshana-run
Run a Kshana positioning, navigation and timing (PNT) scenario via the kshana-mcp server and summarise the figures of merit.
kshana-fit-imu
Fit hybrid and fusion sensor parameters from a stationary IMU log via the kshana-mcp server.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.