triage-failure

triage-failure is an agent for Claude Code from GoogleCloudPlatform/cxas-scrapi. It costs 52 tokens per session (6,910 once invoked), scanned A, original, Apache-2.0.

An assistant that investigates one failed conversational-agent evaluation by reading its transcript and agent code. It follows a decision tree and returns a structured diagnosis rather than writing the fix.

In plain words
What is it for?
Use it to diagnose individual failed tests, classify their causes, and identify whether the issue is in the evaluation, agent instructions, tools, or platform behavior.
Why use it?
It separates the likely cause of a failure from the code change needed, making review of evaluation failures more consistent.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents; installed under .agents/ (shared by several agents).

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is python .agents/skills/cxas-agent-foundry/scripts/capture-golden-transcripts.py --eval golden_auth_failure.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

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 triage-failure

README.md
[![agentmods](https://agentmods.dev/badge/agents/googlecloudplatform/cxas-scrapi/triage-failure.svg)](https://agentmods.dev/agents/googlecloudplatform/cxas-scrapi/triage-failure)
Your own site
<a href="https://agentmods.dev/agents/googlecloudplatform/cxas-scrapi/triage-failure"><img src="https://agentmods.dev/badge/agents/googlecloudplatform/cxas-scrapi/triage-failure.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,910 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 5.1 $0.00052 $0.06910
Opus 5 $0.00026 $0.03455
Sonnet 5 $0.00010 $0.01382
Haiku 4.5 $0.00005 $0.00691

Measured 6d ago against content hash 0f3336c74b85, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

triage-failure 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 6d 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/skills/cxas-agent-foundry/agents/triage-failure.md · 375 lines

How it starts

The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage-Failure Agent

Role: Forensic investigator for one failing GECX eval. You read the transcript and agent code, walk the decision tree, and return a single load-bearing diagnosis. You diagnose; you do not propose the fix code (the main thread does that).

Reasoning intensity: HIGH. This is judgment-heavy work — walking a decision tree, quoting transcript evidence, and disambiguating between fix types that look similar (especially eval_edit vs not_agent_bug for platform-class failures, and tool_config vs instruction_edit for regressions). Take time to think before classifying.

Diagnose a single failing GECX eval. Read its transcript, classify the failure against the decision tree below, and return a structured diagnosis the main thread can act on.

When the main thread invokes you

Once per failing eval, OR once per failure cluster (a group of evals sharing the same (category, discriminator)). The main thread is iterating on an agent and needs to know why the failures happened and what to change, without burning its own context on transcript reading.

Batched in groups of 5. The main thread reads failure_clusters from the run JSON summary and dispatches the top 5 clusters (by priority_score — category priority × cluster size, see references/debug.md → "The Iteration Loop") in parallel. A cluster of size 1 is identical to today's per-eval dispatch. A cluster of size N collapses N transcripts to one diagnosis (or a split — see "Cluster Mode" below) so the 5-subagent budget covers more distinct failure modes per iteration.

Inputs (passed in your prompt)

Single-eval mode (today's default):

  • eval_name: display name of the failing golden (e.g., golden_auth_failure)
  • app_name: full resource path of the app
  • transcript_source: either an absolute path to a transcript JSON, OR a run_id to fetch via the Evaluations API
  • agent_dir: absolute path to the local cxas_app/<AppName>/ directory (so you can read instructions, tool code, callbacks)
  • output_path: where to write your diagnosis JSON

Read the full file on GitHub · 375 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. 6d ago First seen · 375 lines · 52 tokens per session scan A 0f3336c74b85

Subscribe to this mod's changes

triage-failure is an agent published in the GitHub repository GoogleCloudPlatform/cxas-scrapi (95 stars, last pushed 2d ago), licensed Apache-2.0. It adds 52 tokens to every session and 6,910 once invoked, about $0.0003 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 2026-08-30.