api-probe

api-probe is an agent for coding agents from Connected-Mate/corporate-launcher. It costs 46 tokens per session (849 once invoked), scanned A, original, MIT.

A subagent that tests a corporate AI gateway, which is a company-managed service for accessing AI models. It checks the gateway URL, model catalogue, authentication token, and TLS certificate.

In plain words
What is it for?
Use it to verify a gateway endpoint, backend type, available models, authentication, and TLS before making API calls.
Why use it?
It quickly shows whether the gateway connection is usable and identifies basic access or certificate problems before further work begins.

Agent

Part of the corporate-launcher plugin — 1 skill, 1 command, 4 agents shipped together

Install

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.

agentmods
npx agentmods add agents/connected-mate/corporate-launcher/api-probe-subagent
Clone the repo
git clone --depth 1 https://github.com/Connected-Mate/corporate-launcher

Or install corporate-launcher, the plugin that ships this one along with the rest of its 1 skill, 1 command, 4 agents.

Wrote 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.

agentmods badge for api-probe

README.md
[![agentmods](https://agentmods.dev/badge/agents/connected-mate/corporate-launcher/api-probe-subagent.svg)](https://agentmods.dev/agents/connected-mate/corporate-launcher/api-probe-subagent)
Your own site
<a href="https://agentmods.dev/agents/connected-mate/corporate-launcher/api-probe-subagent"><img src="https://agentmods.dev/badge/agents/connected-mate/corporate-launcher/api-probe-subagent.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 849 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.00849
Opus 5 $0.00023 $0.00425
Sonnet 5 $0.00009 $0.00170
Haiku 4.5 $0.00005 $0.00085

Measured 4d ago against content hash 9c470c0274eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-probe 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 4d 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.

agents/api-probe-subagent.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

api-probe subagent

What

Runs scripts/api-probe.py against a corporate AI gateway and returns a 3-line summary to the main conversation. All network noise, JSON payloads, and TLS chain details stay in the fork context.

Input

Caller must provide:

  • --url <BASE_URL> — gateway base, e.g. https://ai-gateway.corp.example/v1
  • --backend <NAME> — one of auto|anthropic|openai|azure|vertex|litellm|bedrock-proxy
  • API_TOKEN — auth token exported as env var only, never passed on the command line by the caller and never echoed in shell history.

Workflow

  1. Read the token from the env var API_TOKEN. If empty, return FAIL: missing API_TOKEN env var and stop.

  2. Run the probe in a single bash invocation that pulls the token from the environment at exec time:

    API_TOKEN="$API_TOKEN" python3 "${CLAUDE_SKILL_DIR}/scripts/api-probe.py" \
      --url "<URL>" \
      --backend "<BACKEND>" \
      --token "$API_TOKEN" 2>&1
    

    Capture exit code and stdout. The token lives in argv only inside the forked process; it never appears in our reply.

  3. Parse the JSON report (ok, latency_ms, models_available, tls.expires, tls.cert_issuer, warnings, error).

  4. Emit a 3-line summary to the parent:

    Gateway reachable (245ms), 6 models available, TLS cert valid until 2027-01-15
    Backend: openai (bearer-token), warnings: none
    Token preview: sk-a...x9k2 — OK
    

Exit-code mapping

Code Meaning Remediation hint to surface
0 OK None — emit success summary.
2 auth failure (401/403) Token expired or wrong header style — re-issue from IdP.
3 network / DNS / timeout Check VPN, corporate proxy (HTTPS_PROXY), URL typo.
4 TLS cert error Install corp CA bundle, set REQUESTS_CA_BUNDLE.
5 bad CLI args Verify --url scheme is http(s):// and host is non-empty.

Read the full file on GitHub · 92 lines

Changes

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.

  1. 4d ago First seen · 92 lines · 46 tokens per session scan A 9c470c0274eb

Subscribe to this mod's changes

api-probe is an agent published in the GitHub repository Connected-Mate/corporate-launcher (3 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 849 once invoked, about $0.0002 per session on Opus 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 2026-08-31.