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-compliance-proxy/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-compliance-proxy)<a href="https://agentmods.dev/skills/alphabitcore/nexus-gateway/test-compliance-proxy"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/test-compliance-proxy.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 Supply Chain · line 89 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- medium Data Exfiltration · line 239 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Excessive Agency · line 398 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 | $0.00135 | $0.05086 |
| Opus 5 | $0.00068 | $0.02543 |
| Sonnet 5 | $0.00027 | $0.01017 |
| Haiku 4.5 | $0.00014 | $0.00509 |
Grade A, and why
test-compliance-proxy 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 8d 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.
through the proxy using a curl form like: How it starts
The opening of the file, as written. The whole thing — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Compliance Proxy
End-to-end smoke test against a running Compliance Proxy:
- MITM proxy on
localhost:3128(this is the proxy port —:3040is the runtime API, not the proxy) - Runtime API on
127.0.0.1:3040(healthz, killswitch) - Metrics on
:9090 - CA cert at
packages/compliance-proxy/dev-certs/ca.crt
For each enabled (Provider, Credential) pair in the DB whose adapter
type uses bearer / API-key auth (openai / anthropic / gemini / glm /
deepseek / minimax — bedrock & vertex are out of scope, they use cloud
SDK auth), this skill issues a non-streaming and a streaming chat call
through the proxy using a curl form like:
curl --proxy http://localhost:3128 \
--cacert packages/compliance-proxy/dev-certs/ca.crt \
-H "Authorization: Bearer <plaintext-provider-key>" \
<baseUrl><pathPrefix><adapter-specific-chat-path>
then verifies a matching traffic_event row exists with source = 'compliance-proxy' and target_host set to the provider host.
When to use
- User typed
/test-compliance-proxyor asked something like "smoke test the compliance proxy", "verify CP MITM works". - After changing code under
packages/compliance-proxy/orpackages/shared/{policy/pipeline,policy/hooks,transport/streaming,audit}/. - When debugging why CP
traffic_eventrows are missing fields.
Inputs
| Arg | Required | Notes |
|---|---|---|
--provider <name> |
no | Scope to one provider by name (Provider.name). Default: all eligible. |
--dry-run |
no | Print the planned (provider, model) test matrix without firing requests. |
--no-stream |
no | Skip the SSE pass for every provider. |
Workflow
preflight → metrics t0 → resolve test matrix → obtain plaintext keys →
domain allowlist check → per-provider chat (non-stream + stream) →
DB verify → metrics delta → report → on-failure: fix-build-restart loop
1. Preflight
curl -fsS http://127.0.0.1:3040/healthz # runtime API
curl -fsS http://localhost:9090/metrics | head -1 # metrics
test -f packages/compliance-proxy/dev-certs/ca.crt # CA present
openssl x509 -in packages/compliance-proxy/dev-certs/ca.crt -noout -subject -dates
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.
- 8d ago First seen · 442 lines · 135 tokens per session scan A ea403a6ba032
test-compliance-proxy is a skill published in the GitHub repository AlphaBitCore/nexus-gateway (23 stars, last pushed 6d ago), licensed Apache-2.0. It adds 135 tokens to every session and 5,086 once invoked, about $0.0007 per session on Opus 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…
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.
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
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.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.