What is cxas-agent-foundry?

A workflow for building and maintaining GECX conversational agents, which are software systems that communicate with people. It covers creating agents from requirements, testing them, finding failures, and improving them.

Use it to turn product requirements into conversational agents, create test data and simulations, test tool and callback behavior, investigate failures, and prepare agents for production.

It gives developers a defined process for checking whether an agent behaves correctly instead of relying on informal manual testing. Its required checklist also helps prevent skipped build, test, or deployment steps.

cxas-agent-foundry — Skill for Claude Code and Codex by GoogleCloudPla

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/GoogleCloudPlatform/cxas-scrapi

agentmods

npx agentmods add skills/googlecloudplatform/cxas-scrapi/cxas-agent-foundry

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/googlecloudplatform/cxas-scrapi/cxas-agent-foundry.svg)](https://agentmods.dev/skills/googlecloudplatform/cxas-scrapi/cxas-agent-foundry)

Your own site

<a href="https://agentmods.dev/skills/googlecloudplatform/cxas-scrapi/cxas-agent-foundry"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/cxas-scrapi/cxas-agent-foundry.svg" alt="Measured on agentmods" height="20"></a>

Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,306 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 warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 14
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00112	$0.02306
Opus 5	$0.00056	$0.01153
Sonnet 5	$0.00022	$0.00461
Haiku 4.5	$0.00011	$0.00231

Measured 4d ago against content hash 0363b9835dcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cxas-agent-foundry 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.

The scan reads SKILL.md. This mod also ships 21 executable files (assets/project-template/cxas_app/Sample_Support_Agent/agents/root_agent/after_model_callbacks/after_model_callbacks_01/python_code.py, assets/project-template/cxas_app/Sample_Support_Agent/agents/root_agent/before_agent_callbacks/before_agent_callbacks_01/python_code.py, assets/project-template/cxas_app/Sample_Support_Agent/agents/root_agent/before_model_callbacks/before_model_callbacks_01/python_code.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Foundry

End-to-end lifecycle for GECX conversational agents: build, test, debug, iterate.

Step tracking — MANDATORY (Phase 0, blocking)

Before doing ANY work — including running setup, asking questions, or scaffolding files — initialize <project>/todo.md from the relevant sub-skill's checklist (verbatim). The checklist is a contract, not a suggestion. If todo.md doesn't exist for the current task, refuse to proceed and create it first.

Long debug/build runs skip verification steps under pressure (e.g., pushing without linting, scaffolding without a TDD, claiming "deployed" without actually pushing). The checklist exists because of this. The instinct to skip a step is the moment the checklist earns its keep — that's when you must consult it, not the moment to bypass it.

Quick Reference

# Lint: dispatch agents/lint-fixer.md sub-agent — DO NOT run `cxas lint` on the main thread.
# Lint output is verbose; keep it inside the sub-agent context.

# Push local files to platform (only after lint-fixer returns status: clean)
cxas push --app-dir <project>/cxas_app/<AppName> \
  --to projects/<project_id>/locations/<location>/apps/<app_id> \
  --project-id <project_id> --location <location>

# Pull platform state to local
cxas pull projects/<project_id>/locations/<location>/apps/<app_id> \
  --project-id <project_id> --location <location> --target-dir <project>/cxas_app/

# Run evals + triage + report (single command)
python .agents/skills/cxas-agent-foundry/scripts/run-and-report.py --message "what changed" --runs 5

# Generate dynamic interactive HTML dashboard with Gemini LLM failure clustering and parameter filters
python .agents/skills/cxas-agent-foundry/scripts/generate_interactive_report.py --input <path_to_sim_results.json> --output <path_to_report.html>

# Inspect app architecture
python .agents/skills/cxas-agent-foundry/scripts/inspect-app.py

# Triage failures
python .agents/skills/cxas-agent-foundry/scripts/triage-results.py --last 3

# Run all 6 build-verification gates against the deployed app
python .agents/skills/cxas-agent-foundry/scripts/gate-check.py

# Tune scoring thresholds (similarity, hallucination, extra-tools)
python .agents/skills/cxas-agent-foundry/scripts/app-thresholds.py show

# Sync callback Python code into evals/callback_tests/agents/ + create test.py symlinks.
# Required for tests to be discoverable by test_all_callbacks_in_app_dir.
python .agents/skills/cxas-agent-foundry/scripts/sync-callbacks.py                  # post-push: pull from platform
python .agents/skills/cxas-agent-foundry/scripts/sync-callbacks.py --from-local <app_dir>  # pre-push: copy from local app dir

# Snapshot app version (create immutable platform backup)
cxas versions create --app-name projects/<project_id>/locations/<location>/apps/<app_id> \
  --display-name "v1.0.0-snapshot" --description "Pre-refactor baseline"

# List and compare app versions
cxas versions list --app-name projects/<project_id>/locations/<location>/apps/<app_id>
cxas versions compare --app-name projects/<project_id>/locations/<location>/apps/<app_id> \
  --source <version_id_1> --target <version_id_2> --web

# Cold-start setup (first-time only — venv + project bootstrap)
.agents/skills/cxas-agent-foundry/scripts/setup.sh
python .agents/skills/cxas-agent-foundry/scripts/setup-project.py

Read the full file on GitHub · 133 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

4d ago Changed · +10 lines 0363b9835dcc
8d ago First seen · 123 lines · 112 tokens per session scan A 6326a19b10b1

Subscribe to this mod's changes

cxas-agent-foundry is a skill published in the GitHub repository GoogleCloudPlatform/cxas-scrapi (95 stars, last pushed today), licensed Apache-2.0. It adds 112 tokens to every session and 2,306 once invoked, about $0.0006 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.

Building agents Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

cxas-agent-foundry