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 jterratsdev/ableton-live-mcp --skill qa-evidence-packgit clone --depth 1 https://github.com/jterratsdev/ableton-live-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/skills/jterratsdev/ableton-live-mcp/qa-evidence-pack)<a href="https://agentmods.dev/skills/jterratsdev/ableton-live-mcp/qa-evidence-pack"><img src="https://agentmods.dev/badge/skills/jterratsdev/ableton-live-mcp/qa-evidence-pack/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/jterratsdev/ableton-live-mcp/qa-evidence-pack"><img src="https://agentmods.dev/badge/skills/jterratsdev/ableton-live-mcp/qa-evidence-pack.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 | $0.00000 | $0.00774 |
| Opus 5 | $0.00000 | $0.00387 |
| Sonnet 5 | $0.00000 | $0.00155 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
qa-evidence-pack 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 8d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Evidence Pack
Build reviewable QA evidence packs that prove observable outcomes against acceptance criteria without loading a large QA playbook into every task.
When To Load
- Trigger:
qa evidence - Trigger:
test evidence - Trigger:
acceptance criteria coverage - Trigger:
playwright - Trigger:
e2e - Trigger:
screenshot - Trigger:
trace - Trigger:
video - Trigger:
visual diff - Trigger:
annotated screenshot - Trigger:
cli output - Trigger:
stdout - Trigger:
stderr - Trigger:
api contract - Trigger:
integration - Trigger:
webhook
Procedure
- Identify the GitHub issue, user story, Orchestra task, and acceptance criteria.
- Create or update a compact evidence report instead of pasting raw logs into the agent context.
- Map every acceptance criterion to one of: automated, manual, contract/mock, external verification, deferred with owner and rationale.
- Capture observable outcomes, not only command execution:
- Web: visible state, key screenshots, Playwright trace, video for failures or critical flows, viewport/device.
- CLI: command, exit code, stdout/stderr expectations, created/changed files, emitted events, final state.
- API: request shape, response contract, error contract, idempotency when relevant, side effects.
- Integration: sandbox/mock receiver result, webhook/event/log, correlation ID, database/query evidence, or explicit deferral.
- Visual/UI/diagram: source or expected image, actual image, diff image when practical, annotated image for defects.
- For visual bugs, create an annotated screenshot using concise overlays:
- red rectangle for clipped, overlapping, or incorrect element bounds;
- orange arrow for wrong connector, anchor, or flow direction;
- yellow translucent area for excess whitespace or spacing defect;
- blue guide line for expected alignment;
- short label naming the defect.
- Store large artifacts as files and reference paths from the report. Summarize only the relevant finding in the handoff.
- Ask BA/Product to compare evidence against story and acceptance criteria, and Architect to review technical coverage before release.
What ships with it
1 file 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.
- 8d ago First seen · 111 lines · 0 tokens per session scan A 1fee6ccea699
qa-evidence-pack is a skill published in the GitHub repository jterratsdev/ableton-live-mcp (0 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 774 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 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.