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 bdfinst/agentic-dev-team --skill test-designgit clone --depth 1 https://github.com/bdfinst/agentic-dev-teamWrote 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/bdfinst/agentic-dev-team/test-design)<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/test-design"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/test-design/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/bdfinst/agentic-dev-team/test-design"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/test-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00136 | $0.02172 |
| Opus 5.5 | $0.00054 | $0.00869 |
| Sonnet 5.5 | $0.00027 | $0.00434 |
| Haiku 4.5 | $0.00014 | $0.00217 |
Grade A, and why
test-design 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Design
Role: orchestrator. This command dispatches the two test review agents as sub-agents and the test-design-advisor skill, then aggregates one report. It does not review files itself — it coordinates.
This command is executed under orchestrator direction. Dispatch each agent with
its model:/effort: frontmatter as declared — the harness resolves both
fields natively before dispatch, per Model/Effort Resolution in
agents/orchestrator.md (ADR 0026).
Orchestrator constraints
- Advisory only. Aggregate findings and recommendations. Do not edit
production code or write test files. Hand actionable fixes to
/apply-fixesor/build. - Dispatch in parallel.
test-reviewandtest-smell-revieware independent — spawn them in one batch for context isolation; each returns structured JSON, not file dumps. - No double-reporting. Apply
knowledge/test-review-division-of-labor.md: when the same line appears in bothtest-reviewandtest-smell-review, keep the design-level framing and drop the duplicate — record every such drop in the report's### Suppressed duplicatessection (see step 6). Fortest-smell-reviewandtest-design-advisor, no de-duplication is required: per the "test-smell-review ↔ test-design-advisor — remedy division" section of the knowledge doc, the smell agent cites the remedy family (viaremedyFamily) and the advisor names the specific remedy pattern and refactor sequence — smell rows and advisor rows join structurally onremedyFamily, not by prose match. - Be concise. One aggregated report. Issue messages one sentence; recommendations map to a concrete next edit.
- MinimumCD vocabulary. Layer labels in the aggregated report use the
MinimumCD six test types (static analysis / unit / component / contract /
integration / E2E) from
knowledge/cd-test-architecture.md. Prefer "contract test" over "narrow integration test"; if you must use the alias, gloss it once:contract test (also called narrow integration test). Define each test type on first use (one-line gloss inline or a "Test type definitions used in this report" block at the top). - No target-shape tables. Per
knowledge/cd-test-architecture.md#the-pyramid-is-a-cost-heuristic-not-a-target-shape, do not emit "current shape vs recommended shape" tables or per-layer target counts; the aggregated report carries the advisor's per-behavior placement table, not a silhouette target. - E2E justification gate. Forward the advisor's four-condition E2E verdict
verbatim (the gate is canonical in
knowledge/cd-test-architecture.md#the-e2e-justification-gate). Never recommend E2E in the rollup without it.
What ships with it
1 file 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.
- 1mo ago First seen · 178 lines · 136 tokens per session scan A 604d41bdc2cd
test-design is a skill published in the GitHub repository bdfinst/agentic-dev-team (295 stars, last pushed 4d ago), licensed MIT. It adds 136 tokens to every session and 2,172 once invoked, about $0.0005 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 2026-09-03.
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.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
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.