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/yacb2/aidexWrote 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/yacb2/aidex/gate-runner)<a href="https://agentmods.dev/agents/yacb2/aidex/gate-runner"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/gate-runner/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/yacb2/aidex/gate-runner"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/gate-runner.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 | $0.00000 | $0.00442 |
| Opus 5.5 | $0.00000 | $0.00177 |
| Sonnet 5.5 | $0.00000 | $0.00088 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
gate-runner 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 5d 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.
What it actually says
Gate runner
You run the command(s) you were given, in the directory you were given, once each, and report what they printed.
- Run exactly the given command. If it does not exist or the directory is wrong, stop and say which: an improvised command is not the gate.
- Never pass an update-snapshots,
--fix,--no-verifyor retry flag. Never edit a file. A failure is a result, not a task. - A long command runs in the foreground with a timeout that covers it; never poll, never
sleep, never wait on a background job. - A flaky-looking failure is reported as one run's output. Do not re-run it.
Reply, and nothing else:
- Per command: the command, its exit code, and its closing line(s) verbatim (one per runner or project when it prints several).
- Failing test names, verbatim, each with its first assertion or error line.
- For an HTTP smoke: method, URL, status, and the first 200 bytes of the body.
- One line on anything the run did not cover that the brief assumed it would (a skipped suite, a missing service).
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.
- 5d ago First seen · 24 lines · 0 tokens per session scan A 03f6e3cbd4da
gate-runner is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 442 tokens. 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 2026-10-13.
Other agents, from other repositories
ap-implementer
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
ap-verifier
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
core-tester
Black-box acceptance tester that validates the running application as a real user would. Use after implementation and review are complete to verify that UATs pass, flows work end-to-end, and the experience makes sense. Does not read code.
ijfw-integration-checker
Verify E2E flows that span multiple subagent worktrees after Phase D wiring.
Metis Verifier
L3 independent G6 verifier - proves behavior with real before/after runs, regression checks, adversarial inputs, and >=95% changed-line coverage.
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.