What is close_unfinished_code?

A workflow for finishing missing, placeholder, or stubbed code in an existing repository. It requires test-driven development (TDD), which means writing a failing test before the implementation, and real hardware-in-the-loop checks for mixer behavior.

Use it to find unfinished implementations, add failing tests, implement the smallest needed change, run the tests, and validate connected PreSonus StudioLive hardware.

It prevents incomplete code from being hidden behind passing mocks and ensures changes follow the repository's lifecycle and evidence requirements.

How zarfld/presonus-studiolive-mcp configures GitHub Copilot

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/close_unfinished_code.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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/zarfld/presonus-studiolive-mcp/close_unfinished_code/github.svg)](https://agentmods.dev/commands/zarfld/presonus-studiolive-mcp/close_unfinished_code)

Your own site

<a href="https://agentmods.dev/commands/zarfld/presonus-studiolive-mcp/close_unfinished_code"><img src="https://agentmods.dev/badge/commands/zarfld/presonus-studiolive-mcp/close_unfinished_code/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/zarfld/presonus-studiolive-mcp/close_unfinished_code"><img src="https://agentmods.dev/badge/commands/zarfld/presonus-studiolive-mcp/close_unfinished_code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,068 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.02068
Opus 5	$0.00000	$0.01034
Sonnet 5	$0.00000	$0.00414
Haiku 4.5	$0.00000	$0.00207

Measured yesterday against content hash 09b133a14d0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

close_unfinished_code 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/close_unfinished_code.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are working inside the already-loaded repository zarfld/presonus-studiolive-mcp.

Primary objective: close the most critical unfinished-code, placeholder, and stub-implementation gaps without bypassing the repository-defined lifecycle process. You must use TDD. HIL validation must use real connected PreSonus StudioLive hardware, not mocks or assumptions.

Non-negotiable rules

Do not start implementation immediately.
First discover and follow the repository’s defined lifecycle/process exactly.
Use the repository workflow in this order unless the repo defines a stricter one:
- requirements
- architecture impact
- design
- tests
- implementation
- HIL validation
- documentation/capability matrix update
- release-readiness/traceability update
Use TDD:
- write or update failing tests first;
- prove they fail for the current implementation;
- implement the smallest change required;
- prove tests pass;
- then perform HIL validation with real mixers.
Do not claim a feature is supported unless there is evidence:
- unit/integration test evidence;
- real hardware-in-loop evidence where mixer behavior is involved;
- documented model and firmware metadata;
- updated capability classification.
Do not replace unknown behavior with guessed logic.
Do not convert stubs into fake success responses.
Do not mark stub, probe_required, inferred, or not_verifiable tools as complete unless the evidence threshold is met.
Write tools must remain disabled by default and safety-gated.
If real hardware is unavailable or not detected, stop before HIL-dependent implementation claims. You may still add failing tests, probe plans, documentation, and safe scaffolding, but you must not mark HIL-dependent work as observed or supported.

Skills to use

If these skills exist in the repo, use them explicitly and follow their contracts:

.github/skills/stub-placeholder-elimination/SKILL.md
.github/skills/mcp-capability-contract/SKILL.md
.github/skills/routing-reverse-engineering/SKILL.md
.github/skills/hil-probe-design/SKILL.md
.github/skills/mcp-write-safety-gate/SKILL.md
.github/skills/fat-channel-calibration/SKILL.md
.github/skills/traceability-enforcement/SKILL.md
.github/skills/release-readiness-audit/SKILL.md
.github/skills/dependency-ci-hygiene/SKILL.md
.github/skills/github-housekeeping/SKILL.md

Read the full file on GitHub · 335 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.

yesterday First seen · 335 lines · 0 tokens per session scan A 09b133a14d0e

Subscribe to this mod's changes

close_unfinished_code is a command published in the GitHub repository zarfld/presonus-studiolive-mcp (1 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,068 tokens. 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.

Debugging TDD Testing

presonus-studiolive-mcp: Command for GitHub Copilot