presonus-studiolive-mcp: Command for GitHub Copilot

.github/prompts/corrective-action-loop.prompt.md

corrective-action-loop is a command for GitHub Copilot from zarfld/presonus-studiolive-mcp. It costs 44 tokens per session (3,796 once invoked), scanned A, original, MIT.

A corrective-action workflow for a verified software defect or other gap. It sends the problem back through the relevant stages—requirements, design, implementation, integration, and testing—and records the fix and its verification.

In plain words
What is it for?
Use it to create a corrective-action report, link the issue to its lifecycle stages, reintegrate the change, and run regression checks.
Why use it?
It reduces the risk of fixing only the visible symptom or introducing a regression, meaning a new failure in previously working behavior.

Command for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt.

This is zarfld/presonus-studiolive-mcp's own configuration. It tells GitHub Copilot how to work on presonus-studiolive-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything presonus-studiolive-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/zarfld/presonus-studiolive-mcp/master/.github/prompts/corrective-action-loop.prompt.md
Clone the repo
git clone --depth 1 https://github.com/zarfld/presonus-studiolive-mcp

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for corrective-action-loop

README.md
[![agentmods](https://agentmods.dev/badge/commands/zarfld/presonus-studiolive-mcp/corrective-action-loop/github.svg)](https://agentmods.dev/commands/zarfld/presonus-studiolive-mcp/corrective-action-loop)
Your own site
<a href="https://agentmods.dev/commands/zarfld/presonus-studiolive-mcp/corrective-action-loop"><img src="https://agentmods.dev/badge/commands/zarfld/presonus-studiolive-mcp/corrective-action-loop/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.

agentmods 80×15 button for corrective-action-loop

Your own site · 80×15
<a href="https://agentmods.dev/commands/zarfld/presonus-studiolive-mcp/corrective-action-loop"><img src="https://agentmods.dev/badge/commands/zarfld/presonus-studiolive-mcp/corrective-action-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,796 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.03796
Opus 5 $0.00022 $0.01898
Sonnet 5 $0.00009 $0.00759
Haiku 4.5 $0.00004 $0.00380

Measured yesterday against content hash 6030ca04f913, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

corrective-action-loop 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 yesterday.

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.

.github/prompts/corrective-action-loop.prompt.md · 342 lines

How it starts

The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🔁 Corrective-Action Loop Prompt

Use this prompt when a verified gap / anomaly / defect is discovered during any Verification & Validation (V&V) activity and must be cycled back through the lifecycle (requirements → architecture → design → implementation → integration → V&V) to ensure the fix is correctly applied, re‑integrated, and re‑verified without introducing regressions.

This workflow aligns with:

  • IEEE 1012-2016 (Verification & Validation)
  • ISO/IEC/IEEE 12207:2017 (Technical & Maintenance Processes)
  • ISO/IEC/IEEE 29148:2018 (Requirements traceability)
  • IEEE 1044 (Anomaly classification) (conceptual reference)
  • Repository conventions (traceability IDs, lifecycle phases, reliability gates)

📤 EXPECTED OUTPUT

Produce a Corrective Action Package (CAP) markdown document with the following structure:

# Corrective Action Package (CAP)
ID: CAP-[YYYYMMDD]-[SEQ]
Anomaly ID(s): ANOM-[ID], DEF-[ID]
Date Opened: [YYYY-MM-DD]
Owner: [Name]
Integrity Level: [Level 1–4]
Status: {OPEN|IN_PROGRESS|AWAITING_REVERIFY|CLOSED}

## 1. Summary
- Detected In Phase: [06-integration / 07-verification-validation / etc.]
- Detection Activity / Test ID: [TEST-INT-APIAuthFlow]
- Defect Description (Concise):
- User Impact (If Released):
- Severity (FDSC Scale / Business Impact):
- Integrity Level Affected Components:

## 2. Objective Evidence of Failure
| Evidence Type | Reference | Notes |
|--------------|-----------|-------|
| Failing Test | TEST-INT-APIAuthFlow | Reproduces handshake mismatch |
| Log Extract | log-2025-11-08T12:45Z | 500 during token refresh |
| Screenshot (if UI) | evidence/img/auth-refresh.png |  |
| Metrics Spike | METRIC-AUTH-ERROR-RATE | Error rate > gate |

## 3. Root Cause Analysis
- Originating Lifecycle Phase: [Design Definition / Requirements / Implementation]
- Fault Class (e.g., Interface mismatch, Timing, Logic, Data contract):
- Why Introduced? (5-Whys or causal chain)
- Why Not Detected Earlier? (Gap in test / review / spec)
- Contributing Conditions (environmental, concurrency, configuration):

## 4. Impact & Change Scope
| Dimension | Assessment |
|-----------|------------|
| Affected Components | [List modules / services] |
| Coupled Elements | [Interfaces / downstream consumers] |
| Requirements Impacted | REQ-F-021, REQ-NF-005 |
| Design Elements | DES-C-014 (AuthAdapter), DES-IF-007 |
| Architecture Views | Logical, Interface View (update needed?) |
| SFMEA Impact | FM-012 RPN re-evaluation required |
| Reliability Gates | Integration pass rate, MTBF trend unaffected / affected |
| Security / Safety | [If applicable] |

## 5. Change Plan
| Action ID | Type | Description | Owner | Phase Routed To | Preconditions |
|----------|------|-------------|-------|-----------------|---------------|
| ACT-01 | Requirement Update | Clarify token refresh timeout semantics | BA Lead | 02-requirements | Stakeholder approval |
| ACT-02 | Interface Adjustment | Align AuthService refresh contract | Dev Lead | 04-design | ACT-01 complete |
| ACT-03 | Code Fix | Implement adjusted retry / backoff | Dev Team | 05-implementation | ACT-02 merged |
| ACT-04 | Test Additions | Add failing test (system + unit) | QA | 06-integration | Code fix PR open |

## 6. Verification & Validation Iteration Strategy
- Task Iteration Policy Triggered? [Yes/No]
- Re-Verification Scope Determination Method: [Risk-based / Full Regression / Impact-based]
- Regression Test Set Selected: [List test IDs]
- Integrity Level Adjustment? [If Yes → justification]

## 7. Test Artifacts Added / Updated
| Test ID | Type | Purpose | New/Updated | Linked Requirement(s) |
|---------|------|---------|-------------|-----------------------|
| TEST-UNIT-AuthRefreshTimeout | Unit | Reproduce boundary condition | New | REQ-F-021 |
| TEST-INT-APIAuthFlow | Integration | Validate multi-step token renewal | Updated (added scenario) | REQ-F-021 |
| TEST-SYS-SessionResilience | System | Validate session persistence under failures | New | REQ-NF-005 |

## 8. Execution & Evidence
| Step | Description | Result | Evidence Ref |
|------|-------------|--------|--------------|
| 1 | Added failing unit test | FAIL (expected) | TEST-UNIT log |
| 2 | Implemented fix (PR 123) | Build PASS | CI-Run-456 |
| 3 | Unit + Integration Regression | PASS (98 tests) | CI-Run-457 |
| 4 | System Reliability Metrics | Stable (λ decreasing) | Metrics snapshot |

## 9. Traceability Updates
| Artifact Type | ID | Updated? | Link |
|--------------|----|----------|------|
| Requirement | REQ-F-021 | Yes | commit abc123 |
| Design | DES-IF-007 | Yes | ADR-023 |
| Code | src/auth/RefreshService.ts | Yes | PR 123 |
| Test | TEST-UNIT-AuthRefreshTimeout | New | /tests/unit/auth/... |
| SFMEA | FM-012 | RPN revised 180→120 | SFMEA-Auth.md |

## 10. Risk & Integrity Review
- Residual Risk Rating: [Low/Medium/High]
- SFMEA Adjusted? [Yes/No]
- CIL Item Created/Closed? [ID]
- New Hazards Introduced? [If yes → Hazard Log ref]

## 11. Closure Criteria
| Criterion | Status |
|-----------|--------|
| All planned actions complete | ✅ |
| All new/updated tests passing | ✅ |
| Regression suite green | ✅ |
| Traceability matrix updated | ✅ |
| Integrity level re-assessed | ✅ / N/A |
| Stakeholder sign-off obtained | Pending / ✅ |

## 12. Lessons Learned
- Prevention Opportunity:
- Missing Control Identified:
- Action to Institutionalize Learning (e.g., checklist update):

## 13. Sign-Off
| Role | Name | Date | Approval |
|------|------|------|----------|
| QA Lead | | | |
| Reliability Engineer | | | |
| Product Owner | | | |
| Security (if applicable) | | | |

Status: CLOSED / (auto-close after verification)

Read the full file on GitHub · 342 lines

Changes

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.

  1. yesterday First seen · 342 lines · 44 tokens per session scan A 6030ca04f913

Subscribe to this mod's changes

corrective-action-loop is a command published in the GitHub repository zarfld/presonus-studiolive-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 3,796 once invoked, about $0.0002 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 2026-09-08.