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 makifbaysal/tasktrooper --skill analytics-result-qagit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/analytics-result-qa)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/analytics-result-qa"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/analytics-result-qa/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/makifbaysal/tasktrooper/analytics-result-qa"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/analytics-result-qa.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 | $0.00069 | $0.01439 |
| Opus 5.5 | $0.00028 | $0.00576 |
| Sonnet 5.5 | $0.00014 | $0.00288 |
| Haiku 4.5 | $0.00007 | $0.00144 |
Grade A, and why
analytics-result-qa 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 4d 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.
Analytics Result QA
Overview
The dangerous analytics bug is not the query that fails — it is the one that returns a plausible number. A fan-out join, a partial month, a shifted denominator: each produces a result that looks fine and is wrong by 20%. This checklist runs before any number leaves your run, and the checks that can be automated become tests.
Core principle: recompute every headline number a second way, and turn every check you did by hand into a test or a dbt test that keeps doing it.
1. Before computing: the question and the definitions
- Is the analysis answering the question asked, for the population asked? Write the population definition down (who is in, who is excluded and why).
- Is each metric defined the way the people who will read it define it ("active", "churned", "revenue" net or gross)? Where the task is silent, record your definition in the closing message.
- Are the comparison periods and cohorts comparable — same length, same definition, both complete?
2. Pre-delivery checklist
Data quality
- The source tables are the right ones, and you know their as-of date.
- No unexpected gaps in the time range or missing segments.
- Null rates in the columns you use are known and handled on purpose.
- No double counting from duplicate source rows or a join.
- Every filter is intentional; none silently drops a segment.
Calculation
- Aggregation grain matches the question; every non-aggregated column is in the GROUP BY.
- Rates use the right denominator, and the denominator cannot be zero.
- Compared periods have the same length; partial periods are excluded or labelled.
- Join types are right (INNER vs LEFT) and row counts were checked before and after each join.
- Parts sum to the whole, or the difference is explained (overlap, unknown bucket).
Reasonableness
- Magnitudes are plausible (no negative revenue, rates within 0–100%).
- No unexplained jumps in a time series.
- Headline numbers match a known reference (an existing dashboard, finance figures, a previous report) or the gap is explained.
- Edge cases behave: an empty segment, a zero-activity period, a brand-new entity.
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.
- 4d ago First seen · 111 lines · 69 tokens per session scan A eb764d826e09
analytics-result-qa is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 1,439 once invoked, about $0.0003 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 2026-10-09.
Other skills, from other repositories
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
code-review
Use this skill to systematically review code changes for correctness, security, performance, maintainability, and test coverage. Activates after implementation, before merging, or when asked to review a pull request or code change. Produces a structured review report with findings categorized by severity.
tdd
Use this skill to practice test-driven development — writing tests before implementation, using tests to drive design, and validating implementation against pre-written tests. Activates when implementing new functionality, refactoring code, or fixing bugs where regression coverage is needed.
agent-benchmark-suite
Agent skill for benchmark-suite - invoke with $agent-benchmark-suite.
qa-acceptance
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
agent-production-validator
Agent skill for production-validator - invoke with $agent-production-validator.