Borrowing it
Nothing to install: this file belongs to couimet/rangeLink. 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/couimet/rangeLink/main/.claude/skills/qa-suggest/SKILL.mdgit clone --depth 1 https://github.com/couimet/rangeLinkWrote 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/couimet/rangelink/qa-suggest)<a href="https://agentmods.dev/skills/couimet/rangelink/qa-suggest"><img src="https://agentmods.dev/badge/skills/couimet/rangelink/qa-suggest/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/couimet/rangelink/qa-suggest"><img src="https://agentmods.dev/badge/skills/couimet/rangelink/qa-suggest.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 | $0.00038 | $0.02433 |
| Opus 5 | $0.00019 | $0.01216 |
| Sonnet 5 | $0.00008 | $0.00487 |
| Haiku 4.5 | $0.00004 | $0.00243 |
Grade C, and why
qa-suggest scanned grade C with 1 finding 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 10d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- prettier-ignore --> How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Suggest
Suggest new test cases for the current QA cycle by diffing the CHANGELOG against existing TC coverage. No arguments needed — everything is auto-discovered from the project.
Input: None (zero-argument skill)
Step 1: Discovery
Read the extension package.json to get the published version:
Read packages/rangelink-vscode-extension/package.json
Extract:
version— the last published version (e.g.,1.0.0)
The QA YAML lives at qa-test-cases.yaml (stable filename; version context comes from package.json .version and the git tag, not the filename). The version field in package.json holds the last published SemVer.
Step 2: Locate QA YAMLs
Find the current cycle's YAML and the previous version's snapshot:
- Current YAML:
packages/rangelink-vscode-extension/qa/qa-test-cases.yaml(stable filename, no version suffix) - Previous YAML: retrieve from the most recent release tag:
git show <tag>:packages/rangelink-vscode-extension/qa/qa-test-cases.yaml(e.g.,git show vscode-extension-v1.0.0:packages/rangelink-vscode-extension/qa/qa-test-cases.yaml). This is the baseline for diffing.
If the current YAML doesn't exist, STOP: "No QA YAML found at qa/qa-test-cases.yaml."
Read both YAML files in parallel.
YAML structure note: TC entries are nested under test_cases: with indentation ( - id: ...). When searching for TC IDs, use id: without a ^ line-start anchor — the entries are indented.
Step 3: Read CHANGELOG and Integration Tests
Read these in parallel:
packages/rangelink-vscode-extension/CHANGELOG.md— extract only the## [Unreleased]section (stop at the next## [header)packages/rangelink-vscode-extension/src/__integration-tests__/suite/— Glob for*.test.tsfiles and scan two things: (a)suite()/test()names to map scenarios to TC IDs, and (b) which tests callwaitForHumanorwaitForHumanVerdict— those are the assisted ones (see "Choosing the automated value" in Step 6 for why this is the canonical signal)
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.
- 10d ago First seen · 253 lines · 38 tokens per session scan C 7a727468992c
qa-suggest is a skill published in the GitHub repository couimet/rangeLink (10 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 2,433 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
browser-qa-delivery
Validate a Design Studio HTML artifact in the sandbox browser, fix rendering and runtime defects, then deliver exactly the tested file.
omh-agent-evaluation
This is a Hermes-native agent-evaluation workflow skill.
omh-verification-gate
This is a Hermes-native verification-gate workflow skill.
Vizra ADK Evaluation Framework
Test and evaluate AI agents with automated evaluations, assertions, and LLM-as-a-Judge patterns.
test-generator
Generate test templates for unit tests, integration tests, and UI tests using Swift Testing and XCTest. Use when adding tests to iOS/macOS apps.
skill-creator
Create, revise, and evaluate reusable AI workflow skills, including trigger-quality tests. Use when authoring a new skill, repairing an existing skill, or measuring whether its metadata routes correctly.