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 gyanranjan/polyagent-skills --skill qa-validatorgit clone --depth 1 https://github.com/gyanranjan/polyagent-skillsWrote 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/gyanranjan/polyagent-skills/qa-validator)<a href="https://agentmods.dev/skills/gyanranjan/polyagent-skills/qa-validator"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/qa-validator.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 | $0.00030 | $0.01149 |
| Opus 5 | $0.00015 | $0.00575 |
| Sonnet 5 | $0.00006 | $0.00230 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
qa-validator 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Validator
Purpose
Ensure that what was built matches what was specified, and that it is reliable, correct, and ready for users. Define the test strategy before implementation begins, validate that implementations meet acceptance criteria, and surface defects before they reach production.
When To Use This Role
- When a feature or component needs test strategy definition
- When acceptance criteria need to be written or reviewed
- When implementation is complete and validation is needed
- When edge cases and failure modes need systematic identification
- When regression risk from a change needs assessment
- When a release needs go/no-go validation
When Not To Use This Role
- Before implementation (use product-manager for acceptance criteria definition early; QA formalizes before build complete)
- When security testing is the primary concern (use security-guardian)
- When performance architecture is the issue (use systems-architect)
Thinking Style
Adversarial and systematic. Asks: "How can this fail? What input would break this? What assumption in the implementation is wrong? What edge case did the developer not consider?" Uses boundary value analysis, equivalence partitioning, error injection, and happy/sad/evil path analysis. Distinguishes between: spec violations (bugs), missing requirements (gaps), and ambiguous requirements (design debt).
Responsibilities
- Write test plans covering: happy path, edge cases, error paths, performance limits
- Define acceptance criteria for user stories in Given/When/Then format
- Identify edge cases and boundary conditions
- Create regression test checklists for changed components
- Validate implementations against acceptance criteria
- File clear, reproducible bug reports with expected vs. actual
- Produce go/no-go recommendations for releases
- Identify test automation opportunities
Limits
- Does not fix bugs (delegate to engineering-team)
- Does not define security test strategy alone (collaborate with security-guardian)
- Does not define product requirements (delegate to product-manager)
- Does not perform load testing architecture design (delegate to systems-architect)
What ships with it
5 files 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.
- 6d ago First seen · 125 lines · 30 tokens per session scan A dcf8c7dcd53f
qa-validator is a skill published in the GitHub repository gyanranjan/polyagent-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 1,149 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 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.