Borrowing it
Nothing to install: this file belongs to band-app/band. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/band-app/band/main/.claude/skills/write-integration-test/SKILL.mdgit clone --depth 1 https://github.com/band-app/bandWrote 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/band-app/band/write-integration-test)<a href="https://agentmods.dev/skills/band-app/band/write-integration-test"><img src="https://agentmods.dev/badge/skills/band-app/band/write-integration-test/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/band-app/band/write-integration-test"><img src="https://agentmods.dev/badge/skills/band-app/band/write-integration-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 329 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00137 | $0.05886 |
| Opus 5.5 | $0.00055 | $0.02354 |
| Sonnet 5.5 | $0.00027 | $0.01177 |
| Haiku 4.5 | $0.00014 | $0.00589 |
Grade A, and why
write-integration-test scanned grade A with 1 finding 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 13d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const res = await fetch(url, { headers: { Authorization: `Bearer ${TOKEN}` } }); How it starts
The opening of the file, as written. The whole thing — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Integration Tests
This skill is the operational playbook — how to write an integration test against the Band web app. It is NOT the rule list.
- The reviewer-enforced rules live in
.claude/testing-criteria.mdasTEST-1…TEST-35. Open that file once before you write your first test on this repo. Both CI (.github/workflows/claude-review.yml) and the localreview-and-applyskill apply it verbatim to your diff. - The narrative doctrine — why we test this way — lives in
docs/integration-testing.md.
Throughout this playbook, prescriptions that correspond to a specific rule are cited inline as (enforces TEST-N). If you intentionally deviate from one, fix it before pushing or cite the ID in your PR description with a justification — the reviewer will flag every unjustified deviation.
Integration tests are the default proof of correctness for any user-observable change (enforces TEST-6). Unit tests stay useful for non-observable internals and combinatorial cases, but the integration test is what proves the feature works and what guards against the regression you came here to fix.
Architecture — One Picture, Both Layers
Backend and frontend tests share the same server boot and the same fixture model. The only difference is whether the test drives the server through fetch or through a browser.
┌────────────────────────────────────────────────────────────────────┐
│ Test Process │
│ │
│ ┌─────────────┐ │
│ │ Test body │── fetch ──┐ │
│ └─────────────┘ ▼ │
│ │ ┌──────────────────────────────┐ │
│ │ │ Real App Server (production │ │
│ │ │ binary, SSR, auth, tRPC, │ │
│ │ │ migrations, the works) │ │
│ │ └──────────────────────────────┘ │
│ │ │ HTTP (env var override) │
│ │ ▼ │
│ │ ┌──────────────────────────────┐ │
│ │ │ Express stubs (one server │ │
│ │ │ per external service, on │ │
│ │ │ a random port) │ │
│ │ └──────────────────────────────┘ │
│ │ │
│ Frontend tests ONLY: │
│ ┌─────────────────────┐ drives │
│ │ Playwright Browser │ ◄────────────── Test body │
│ │ (Chromium, real) │ │
│ └─────────────────────┘ │
│ │
│ ┌──────────────────────────────────────────────────────────────┐ │
│ │ Testcontainers / temp SQLite — real data layer, ephemeral │ │
│ └──────────────────────────────────────────────────────────────┘ │
└────────────────────────────────────────────────────────────────────┘
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.
- 13d ago Changed 0fec9e1680eb
- 25d ago Changed c3093a3a8440
- 26d ago Changed 93d5c0f643e6
- 2mo ago First seen · 479 lines · 137 tokens per session scan A c2b03797ff33
write-integration-test is a skill published in the GitHub repository band-app/band (5 stars, last pushed today), licensed MIT. It adds 137 tokens to every session and 5,886 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.