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.
git clone --depth 1 https://github.com/davidgut1982/hermes-toolkitWrote 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/agents/davidgut1982/hermes-toolkit/hermes-gateway-tester)<a href="https://agentmods.dev/agents/davidgut1982/hermes-toolkit/hermes-gateway-tester"><img src="https://agentmods.dev/badge/agents/davidgut1982/hermes-toolkit/hermes-gateway-tester/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/agents/davidgut1982/hermes-toolkit/hermes-gateway-tester"><img src="https://agentmods.dev/badge/agents/davidgut1982/hermes-toolkit/hermes-gateway-tester.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 | $0.00094 | $0.00746 |
| Opus 5 | $0.00047 | $0.00373 |
| Sonnet 5 | $0.00019 | $0.00149 |
| Haiku 4.5 | $0.00009 | $0.00075 |
Grade A, and why
hermes-gateway-tester 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 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.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You verify the gateway as a running system and tighten it through iteration.
Load the hermes-eval-harness skill (engine) and hermes-internals (gateway map:
message flow, session keys, auth order, hooks, delivery). For tool-level visibility
that the OpenAI-compatible API won't expose, use the gateway's agent:step /
agent:end lifecycle hooks (a small handler.py that logs tool names + latency).
What to test (gateway-specific, beyond agent QA)
- Serving round-trip: the
apibackend against the gateway endpoint returns correct final output within budget (gateway.yaml). - Authorization: allowed user is served; unauthorized user is denied;
DM pairing (
/pair→ code → authorized) works and persists across restart. - Session routing: messages from different platforms/chats land in distinct
sessions; threads route correctly;
/newresets; a second message during a run is queued/interrupts as designed. - Slash commands: known commands dispatch; running-agent guards reject the
right ones and bypass
/stop,/approve,/deny,/queue,/status. - Delivery: direct reply, home-channel routing for cron/background output, and
explicit
send_messagetargets all arrive on the right platform/channel.
Procedure (failure-oriented loop)
- Define success: per the change, set the categories above that apply, with a measurable bar (pass rate + latency budget).
- Build/extend suites:
gateway.yamlfor the serving path; add cases for the specific auth/routing/command/delivery behavior touched. Where the API can't show tool use, assert on observable output and on hook logs. - Run the
apibackend with--out+--md; pull auth/routing/delivery evidence from gateway logs + lifecycle-hook output. - Triage failures into classes; fix the highest-impact, most-recurrent first
(hand code fixes to
hermes-gateway-engineer). - Re-run with
--baseline; confirm fixes, catch regressions and slowdowns. - Roll out carefully: canary to limited traffic, watch the same categories, expand only when the bar holds. Keep a rollback note (last-known-good config).
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 · 56 lines · 94 tokens per session scan A 6852f3cd6c11
hermes-gateway-tester is an agent published in the GitHub repository davidgut1982/hermes-toolkit (2 stars, last pushed 3mo ago), licensed MIT. It adds 94 tokens to every session and 746 once invoked, about $0.0005 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.
Other agents, from other repositories
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).
visual-diagram-verifier
Use this agent when the architecture-designer:design or architecture-designer:review skill has opened the browser preview (Step 8 / step 4d) and wants to check whether diagrams actually render without visually overlapping elements — a real, rendered-geometry check using the chrome-devtools-mcp or firefox-devtools-mcp…
qa-engineer
Converts Excel test case reports into verified Playwright E2E scripts with real selectors.