xtbench-triangulate

xtbench-triangulate is a skill for Claude Code, Codex from zcaudate-xyz/foundation-base. It costs 46 tokens per session (1,326 once invoked), scanned A, original, MIT.

A guide for investigating failed xtbench GitHub Actions runs. It groups failures across programming languages to show whether the shared test or one language-specific version is likely responsible.

In plain words
What is it for?
Use it to download a CI run, identify failing namespaces, map generated tests to their sources, and choose where to debug.
Why use it?
It narrows the search for the root cause when generated tests fail in different language implementations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to download a CI run, identify failing namespaces, map generated tests to their sources, and choose where to debug.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zcaudate-xyz/foundation-base/xtbench-triangulate
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.

Any agent
npx skills add zcaudate-xyz/foundation-base --skill xtbench-triangulate
Clone the repo
git clone --depth 1 https://github.com/zcaudate-xyz/foundation-base

Made for: Claude Code, Codex.

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 xtbench-triangulate

README.md
[![agentmods](https://agentmods.dev/badge/skills/zcaudate-xyz/foundation-base/xtbench-triangulate/github.svg)](https://agentmods.dev/skills/zcaudate-xyz/foundation-base/xtbench-triangulate)
Your own site
<a href="https://agentmods.dev/skills/zcaudate-xyz/foundation-base/xtbench-triangulate"><img src="https://agentmods.dev/badge/skills/zcaudate-xyz/foundation-base/xtbench-triangulate/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.

agentmods 80×15 button for xtbench-triangulate

Your own site · 80×15
<a href="https://agentmods.dev/skills/zcaudate-xyz/foundation-base/xtbench-triangulate"><img src="https://agentmods.dev/badge/skills/zcaudate-xyz/foundation-base/xtbench-triangulate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00046 $0.01326
Opus 5 $0.00023 $0.00663
Sonnet 5 $0.00009 $0.00265
Haiku 4.5 $0.00005 $0.00133

Measured 10d ago against content hash d19edc6d7f08, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

xtbench-triangulate 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 10d 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.

.kimi/skills/xtbench-triangulate/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

xtbench Error Triangulation

Use this skill when an xtbench CI run is failing and you need to decide whether to look at the original xt.* test/implementation or at a language-specific spec/rewrite.

What it does

Given a GitHub Actions run URL (or run id), it:

  1. Downloads the run logs with gh.
  2. Parses the per-language failing-function summary that lein seedgen test prints.
  3. Maps generated xtbench.<lang>.xt.* namespaces back to their original xt.* source namespaces.
  4. Groups failures by source namespace across languages.
  5. Reports:
    • Shared source namespaces (failing in 2+ languages) → likely an issue in the original test-lang/xt/... test or src-lang/xt/... implementation.
    • Language-specific namespaces (failing in only one language) → likely an issue in that language's spec/rewrite (src/hara/model/spec_<lang>.clj, src/hara/model/spec_<lang>/rewrite.clj).

Prerequisites

  • gh CLI installed and authenticated (gh auth status).
  • Run inside the foundation-base repo root.
  • The run must be for the Run xtbench Tests workflow (.github/workflows/run-xtbench.yml).

Quick usage

From a run URL

lein exec scripts/xtbench_triangulate.clj https://github.com/zcaudate-xyz/foundation-base/actions/runs/28731393184

From a bare run id

lein exec scripts/xtbench_triangulate.clj 28731393184

From an already-downloaded log directory

If you have already extracted the zip of logs:

lein exec scripts/xtbench_triangulate.clj /path/to/extracted-logs

Override the repo

lein exec scripts/xtbench_triangulate.clj 28731393184 --repo my-org/foundation-base

Manual workflow (no helper)

If you cannot use the helper script, do it by hand:

  1. Get the run id from the URL (.../runs/<id>).
  2. Download logs:
    gh api repos/zcaudate-xyz/foundation-base/actions/runs/<id>/logs \
      --method GET -H "Accept: application/vnd.github+json" > logs.zip
    unzip logs.zip -d xtbench-logs
    
  3. Find the top-level job logs: files like 0_04 - xt.db _ dart.txt, 11_01 - xt.lang _ lua.txt.
  4. Extract the seedgen summary: look for the line [seedgen] per-language failing functions: followed by a Clojure map.
  5. Map back to source namespaces:
    • Function symbols like xt.lang.common-repl/notify-with-promise → source ns xt.lang.common-repl.
    • Errored namespaces like xtbench.dart.db.system.impl-sqlite-test → source ns xt.db.system.impl-sqlite-test.
  6. Triangulate: same source ns in multiple languages → original xt.* issue; unique to one language → language spec/rewrite.

Read the full file on GitHub · 127 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. 10d ago First seen · 127 lines · 46 tokens per session scan A d19edc6d7f08

Subscribe to this mod's changes

xtbench-triangulate is a skill published in the GitHub repository zcaudate-xyz/foundation-base (42 stars, last pushed 6d ago), licensed MIT. It adds 46 tokens to every session and 1,326 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 2026-09-02.

Related

Other skills, from other repositories

Verification & Quality Assurance

Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.

ruvnet/RuView · 36 tokens

smoke-test

Health smoke tests + auto-fix for gbrain installs (and OpenClaw services when present). Run after machine/container restarts or whenever something seems broken. Tests critical services, auto-fixes bounded local issues, and reports worker topology without starting daemons. Extensible via user-defined test scripts in…

garrytan/gbrain · 79 tokens

mcore-create-issue

Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.

NVIDIA/skills · 26 tokens

debug-task

Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time when it should be cached, or when outputs are empty or missing after a…

moonrepo/moon · 231 tokens

operating-github-ci-fixer

Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.

Tracer-Cloud/opensre · 48 tokens

ci-triage

Classify CI failures — distinguish clear regressions from infra flakes and security-test failures. Produces structured failure reports.

cobusgreyling/loop-engineering · 28 tokens