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 aigentive/RalphX --skill qa-evaluationgit clone --depth 1 https://github.com/aigentive/RalphXWrote 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/aigentive/ralphx/qa-evaluation)<a href="https://agentmods.dev/skills/aigentive/ralphx/qa-evaluation"><img src="https://agentmods.dev/badge/skills/aigentive/ralphx/qa-evaluation/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/aigentive/ralphx/qa-evaluation"><img src="https://agentmods.dev/badge/skills/aigentive/ralphx/qa-evaluation.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 | $0.00014 | $0.01056 |
| Opus 5.5 | $0.00006 | $0.00422 |
| Sonnet 5.5 | $0.00003 | $0.00211 |
| Haiku 4.5 | $0.00001 | $0.00106 |
Grade A, and why
qa-evaluation 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 1mo 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Evaluation
Guidelines for refining test plans based on actual implementation and evaluating results.
Phase 2A: Refinement Process
1. Analyze Git Diff
git diff HEAD~1 --stat # Overview of changed files
git diff HEAD~1 -- <file> # Specific file changes
git log -1 --oneline # Commit message context
2. Compare Intent vs Reality
- Original acceptance criteria: What was planned
- Git diff: What was actually implemented
- Identify:
- Selectors that changed (testids, classes)
- Features added/removed
- UI structure differences
3. Refine Test Steps
Update test commands to match actual implementation:
- Correct element selectors
- Adjust wait times
- Update expected outcomes
- Add tests for new features
- Remove tests for dropped features
Refinement Output Format
{
"actual_implementation": "Brief summary of what git diff shows was implemented",
"refined_test_steps": [
{
"id": "QA1",
"criteria_id": "AC1",
"description": "Updated description",
"commands": [
"agent-browser open http://localhost:1420",
"agent-browser wait --load",
"agent-browser is visible [data-testid='actual-element']",
"agent-browser screenshot \"$RALPHX_AGENT_SCREENSHOT_DIR/qa1.png\""
],
"expected": "Updated expectation"
}
]
}
Phase 2B: Test Execution
Execution Flow
- Execute each test step in order
- Record pass/fail for each command
- Capture screenshot regardless of outcome
- Continue testing even if step fails
- Calculate overall status
Result Recording
For each step:
- status: "passed" | "failed" | "skipped"
- screenshot: Path to captured image
- actual: What actually happened (if failure)
- expected: What should have happened
- error: Error message (if any)
Test Results Output Format
{
"qa_results": {
"task_id": "task-123",
"overall_status": "passed",
"total_steps": 5,
"passed_steps": 5,
"failed_steps": 0,
"steps": [
{
"step_id": "QA1",
"status": "passed",
"screenshot": "$RALPHX_AGENT_SCREENSHOT_DIR/qa1-result.png",
"actual": null,
"expected": null,
"error": null
}
]
}
}
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.
- 1mo ago First seen · 191 lines · 14 tokens per session scan A 368bcd7956ec
qa-evaluation is a skill published in the GitHub repository aigentive/RalphX (5 stars, last pushed 24d ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,056 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.