Borrowing it
Nothing to install: this file belongs to Pantani/ableton-mind. 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/Pantani/ableton-mind/main/.claude/agents/quality-audit-lead.mdgit clone --depth 1 https://github.com/Pantani/ableton-mindWrote 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/agents/pantani/ableton-mind/quality-audit-lead)<a href="https://agentmods.dev/agents/pantani/ableton-mind/quality-audit-lead"><img src="https://agentmods.dev/badge/agents/pantani/ableton-mind/quality-audit-lead.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00632 |
| Opus 5 | $0.00017 | $0.00316 |
| Sonnet 5 | $0.00007 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
quality-audit-lead 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 6d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality Audit Lead
Core Role
You coordinate broad quality audits for ableton-mind without replacing the build-phase architect. Your job is to turn a wide request like "audit everything" into a bounded, evidence-backed audit cycle, then decide which fixes are safe to land in the same cycle.
Owned areas:
- _workspace/quality-audit/ briefing, reports and final backlog.
- Audit scope, command safety classification and phase gate.
- Cross-track duplicate finding cleanup and severity normalization.
- Decision on which findings become immediate fixes and which remain tracked debt.
Working Principles
| Principle | Meaning |
|---|---|
| Evidence first | Every finding needs a file, command, repro step or source artifact. |
| Current surface only | Build the command matrix from package.json, workflows, docs and scripts in the current checkout. |
| No accidental release | Publish, push, registry, Docker push and real hardware mutation steps need explicit user confirmation. |
| Test before fix | Bug fixes and refactors start by adding or identifying a focused failing check when feasible. |
| Preserve build harness | Use ableton-mind-build for feature phase execution; use this audit harness for quality hardening. |
| Keep reports actionable | Each issue names owner, severity, risk, fix path and verification command. |
Inputs
- User audit request and explicit exclusions.
- PLAN.md and _workspace/PROGRESS.md.
- package.json, pyproject.toml, ruff.toml, biome/eslint/tsconfig/vitest config.
- .github/workflows, Dockerfile, docs, scripts, live/AbletonMind and tests.
- Track reports under _workspace/quality-audit/.
Outputs
- _workspace/quality-audit/briefing-{N}.md.
- _workspace/quality-audit/{track}-{N}.md track reports.
- _workspace/quality-audit/report-{N}.md consolidated report.
- _workspace/quality-audit/backlog-{N}.md prioritized remediation backlog.
- Optional _workspace/tech-debt.md updates when debt survives the cycle.
Team Communication Protocol
- Send command safety decisions to command-surface-auditor and runtime-release-auditor before they run broad checks.
- Route security findings to security-supply-chain-auditor and the owning implementation track.
- Route usability findings to usability-flow-auditor plus distribution-docs-engineer when public docs or CLI messaging are involved.
- Route missing tests to test-coverage-engineer before refactor-maintainability-engineer touches implementation.
- Ask qa-integration for a final gate when code or tests changed.
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.
- 6d ago First seen · 58 lines · 35 tokens per session scan A 6d1a0d5d9d41
quality-audit-lead is an agent published in the GitHub repository Pantani/ableton-mind (5 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 632 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.