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 Jarroslav/agentic-os --skill qa-baselinegit clone --depth 1 https://github.com/Jarroslav/agentic-osWrote 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/jarroslav/agentic-os/qa-baseline)<a href="https://agentmods.dev/skills/jarroslav/agentic-os/qa-baseline"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/qa-baseline/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/jarroslav/agentic-os/qa-baseline"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/qa-baseline.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 | $0.00174 | $0.02105 |
| Opus 5.5 | $0.00070 | $0.00842 |
| Sonnet 5.5 | $0.00035 | $0.00421 |
| Haiku 4.5 | $0.00017 | $0.00211 |
Grade A, and why
qa-baseline 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 2mo 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qa-baseline
Build a durable QA knowledge base by inspecting the current repo and (optionally)
external QA systems, then persisting what you learn as two guide files. Downstream,
qa-scoping reads both files on every feature run — this skill is the one-time
seed that makes that possible.
Blast radius: R2 (writes repo guide files). No file is written until the user approves at the Phase 4 gate. Phase 1 is strictly read-only.
Methodology owner. How qa knowledge is gathered, structured and kept current is defined by the
qa-knowledge-baseblueprint inagentic-qe(skills/qe-blueprints/references/catalog/analyze/qa-knowledge-base.md). This skill executes; the blueprint is the authority on method. If the two ever disagree, the blueprint wins and this file is what gets corrected — one source of truth, so two agents cannot follow two different sets of practices.
When to use
- First-time QA setup in a repo, before any pipeline run.
- Trigger phrases:
qa init,qa foundation,set up qa. - Slash command:
/sdlc:qa-init.
Do not use this to run or author tests — it discovers and configures only.
Outputs (path contract)
| File | Purpose |
|---|---|
.agentic/guides/testing/qa-strategy.md |
How this repo tests: frameworks, types, coverage targets, conventions, anti-patterns, external sources. |
.agentic/guides/testing/qa-health.md |
Current QA state: coverage summary, risky untested areas, test debt, recent activity. |
Both artifacts overwrite on re-run. The skill is idempotent and safe to re-run.
Flow
Five phases, in order. Nothing is written to disk before Phase 5, and Phase 5 is gated on explicit user approval in Phase 4.
Phase 1 — Discovery (read-only)
Scan the current repo for QA signals. For each signal record: absolute path, type, and detected framework. Write nothing.
Signal catalog:
| Type | Paths / patterns |
|---|---|
| Test directories | tests/, __tests__/, spec/, e2e/, cypress/, playwright/ |
| Coverage reports | coverage/, .nyc_output/, htmlcov/, coverage.xml, lcov.info |
| Test config | jest.config.{js,ts,mjs,cjs}, pytest.ini, setup.cfg, playwright.config.{ts,js}, .nycrc, vitest.config.{ts,js} |
| CI test gates | .github/workflows/*.yml, .gitlab-ci.yml, Jenkinsfile — extract steps matching: test, coverage, e2e, playwright, cypress, pytest, jest, vitest |
| Local QA docs | files matching *test-plan*, *test_plan*, *strategy*, *test-cases*, *testcases* |
What ships with it
2 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.
- 2mo ago First seen · 186 lines · 174 tokens per session scan A ac7d7c70c53f
qa-baseline is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 174 tokens to every session and 2,105 once invoked, about $0.0007 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
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".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
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.
tdd
Guided test-driven development workflow for .NET 10 using xUnit v3, WebApplicationFactory, Testcontainers, and Verify snapshots. Follows the strict red-green-refactor cycle. Use when: "TDD", "test-driven", "let's TDD this", "red green refactor", "write the test first", or when building a feature with clear acceptance…