Borrowing it
Nothing to install: this file belongs to AlphaBitCore/nexus-gateway. 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/AlphaBitCore/nexus-gateway/main/.claude/skills/test-all/SKILL.mdgit clone --depth 1 https://github.com/AlphaBitCore/nexus-gatewayWrote 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/alphabitcore/nexus-gateway/test-all)<a href="https://agentmods.dev/skills/alphabitcore/nexus-gateway/test-all"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/test-all/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/alphabitcore/nexus-gateway/test-all"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/test-all.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Privilege Escalation · line 12 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 105 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00167 | $0.01441 |
| Opus 5.5 | $0.00067 | $0.00576 |
| Sonnet 5.5 | $0.00033 | $0.00288 |
| Haiku 4.5 | $0.00017 | $0.00144 |
Grade A, and why
test-all 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
adding "let me also curl X to verify" steps to this skill, that How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test All
Drives tests/run-all.sh end-to-end and reports back. This is the
recommended entry point after any non-trivial code change — it covers
every layer of the test program (docs/developers/architecture/cross-cutting/observability/test-harness-architecture.md) and produces
one report you can paste into a PR or hand to a reviewer.
When to use
- User typed
/test-all,/test-all --quick, or asked something like "run all tests", "regression check", "test everything", "smoke the whole system". - Right before declaring a multi-service change done.
- After a service restart or config change, to confirm everything is still wired up.
Don't use this for narrowly-scoped debugging — pick a single layer (L1 smoke, L1 Go integration, L4 UI) and run that test directly.
Inputs
| Arg | Required | Notes |
|---|---|---|
--quick |
no | Preflight + L1 smoke only (≈ 30 s, no LLM calls). Default mode. |
--full |
no | All phases including L3 AI-judge and L4 Playwright (≈ 3–5 min, costs ~5 Kimi calls). |
--phase <name> |
no | Run only one phase: smoke, go, ui, protocol, ai-judge. |
--no-preflight |
no | Skip preflight (use only when debugging the runner itself). |
If the user did not pass a flag, default to --full. The cost of one full
run (~2 ¢ in Kimi tokens, ~5 minutes wall) is worth it as a green/red
signal; downgrade to --quick only if the user asked for fast feedback.
Prerequisites
Verify before starting (the runner's own preflight will also check; we front-run these so failures surface in chat, not in a buried log):
tests/.env.localexists andNEXUS_TEST_VKis not the placeholdernvk_REPLACE_ME. If missing, instruct the user to copytests/.env.local.exampleand setNEXUS_TEST_VKto a real Nexus VK (theresearch-all-modelsVK is fine for local dev; query the DB if needed:SELECT name, "keyPrefix" FROM "VirtualKey" WHERE enabled = true AND "vkType" = 'application' LIMIT 5;).- Local services running. Quick check:
lsof -nP -iTCP:3001,3040,3050,3060 -sTCP:LISTEN. All four ports must show a listener. If any are missing, ask the user whether to start them (./scripts/dev-start.shis the canonical bootstrap) rather than launching them silently. - Postgres + Redis containers up:
docker ps --filter name=nexus-postgres --filter name=nexus-redis --format '{{.Names}}'.
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 · 124 lines · 167 tokens per session scan A 2a1a4d1dd841
test-all is a skill published in the GitHub repository AlphaBitCore/nexus-gateway (25 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 167 tokens to every session and 1,441 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
verify
Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches…
cli-eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
quality-scan
Run a scoped, read-only quality scan and report exact-candidate evidence, failures and frozen debt. Use for an ad-hoc gate sweep or release preparation; a static scan is not full release acceptance.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.