Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/it235/multica-best-practicesnpx agentmods add skills/it235/multica-best-practices/multica-test-t1-designWrote 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/it235/multica-best-practices/multica-test-t1-design)<a href="https://agentmods.dev/skills/it235/multica-best-practices/multica-test-t1-design"><img src="https://agentmods.dev/badge/skills/it235/multica-best-practices/multica-test-t1-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/it235/multica-best-practices/multica-test-t1-design"><img src="https://agentmods.dev/badge/skills/it235/multica-best-practices/multica-test-t1-design.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 | $0.00062 | $0.01671 |
| Opus 5.5 | $0.00025 | $0.00668 |
| Sonnet 5.5 | $0.00012 | $0.00334 |
| Haiku 4.5 | $0.00006 | $0.00167 |
Grade A, and why
multica-test-t1-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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Design (T1 Test Design · Content + Landing)
Position
The only T1 skill: traceability → cases → full Confluence → review → (after 👤 passphrase) XMind/JIRA; parallel Apifox + automation planning.
Not for T2/T3—T2 see multica-test-t2-coverage; T3 see -t3 + multica-test-orchestration.
| Layer | Skill | Responsibility |
|---|---|---|
| Orchestration | multica-test-orchestration |
Cross-phase routing; automation into repo see references/automation-assets-lifecycle.md |
| T1 | This skill | Content + Confluence + XMind/JIRA after passphrase |
| Platform | multica-platform-* |
Read upstream; Apifox writes scenarios |
| Review | multica-review-test |
Review Confluence; review only, no import |
Three-phase delivery: Phase A is Confluence only (no XMind generated); only Phase C after 👤 passphrase does XMind + JIRA. Details in
references/generation-workflow.md.
Platform Collaboration
| Platform skill | Used for |
|---|---|
multica-platform-jira |
fetch_all → get_issue.py; after passphrase import_to_tracker.py (team-provided, see references/import-contract.md) |
multica-platform-confluence |
Collect fetch_page; publish t1-cases.md (see § Confluence landing) |
multica-platform-figma |
fetch_all → fetch_file.py |
multica-platform-apifox |
T1 parallel write interface scenarios |
| team-knowledge-base (optional) | Step 0.5 terms/entry (binary usage; not bundled in this repo, connect per platform used) |
Credentials: JIRA_USERNAME / JIRA_PASSWORD preferred → see platform skill + data-sources.md.
references/ Index
| File | Purpose |
|---|---|
generation-workflow.md |
Two phases, passphrase, test-management platform naming/validation, steps/priority, dedup/merge |
executability-and-permissions.md |
Permission identification order, dual targets, module naming, post-generation self-check |
output-format.md |
JSON 1:1, generated_summary, coverage self-check table, Output Delivery |
multimodal-content.md |
HTML/image Read and fused understanding |
agent-instructions.md |
Copyable Agent instructions |
design-trace.md |
AC ↔ design traceability |
test-case-template.md |
Functional case fields |
coverage-dimensions.md |
Dimension selection, scale, coverage matrix, XMind |
coverage-checklist.md |
Pre-generation self-check list |
web-ui-checkpoints.md |
Figma → UI test points |
api-testing-guide.md |
Interface scenario patterns |
data-sources.md |
Collection orchestration and credentials |
What ships with it
20 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.
- config.local.env.example 802 B
- references/agent-instructions.md 3.7 KB
- references/api-testing-guide.md 4.7 KB
- references/coverage-checklist.md 7.3 KB
- references/coverage-dimensions.md 2.6 KB
- references/data-sources.md 6.3 KB
- references/design-trace.md 1.4 KB
- references/executability-and-permissions.md 3.8 KB
- references/generation-workflow.md 15 KB
- references/import-contract.md 1.9 KB
- references/multimodal-content.md 2.7 KB
- references/output-format.md 4.4 KB
- references/test-case-template.md 3.7 KB
- references/web-ui-checkpoints.md 4.1 KB
- scripts/dedup_check.py 13 KB runs code
- scripts/fetch_all.py 10 KB runs code
- scripts/generate_test_cases.py 9.4 KB runs code
- scripts/generate_xmind.py 13 KB runs code
- scripts/local_env.py 4.5 KB runs code
- scripts/README.md 2.3 KB
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 Changed · -8 tokens per session ab0e13870188
- 1mo ago First seen · 137 lines · 70 tokens per session scan A 9f5e77fc25fa
multica-test-t1-design is a skill published in the GitHub repository it235/multica-best-practices (212 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 1,671 once invoked, about $0.0002 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 2026-09-07.
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.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.