agentmods.dev

architectural-probe

architectural-probe is an agent for Claude Code from navapbc/digital-service-orchestra. It costs 23 tokens per session (387 once invoked), scanned A, original, Apache-2.0.

An agent that prepares an end-to-end test scaffold or an integration-harness specification for large architectural work. An integration harness is a setup for testing several parts of a system together.

In plain words
What is it for?
Creating a test scaffold or specification that explains how to test an architectural project end to end.
Why use it?
It makes the planned system-wide testing approach explicit before the architectural work is reviewed.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the dso plugin — 37 skills, 4 commands, 53 agents shipped together

not rated 6repo yesterday A scan 23 tokens original Apache-2.0

Good fit Creating a test scaffold or specification that explains how to test an architectural project end to end.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/navapbc/digital-service-orchestra/architectural-probe
View source ↗ navapbc/digital-service-orchestra
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.

Clone the repo
git clone --depth 1 https://github.com/navapbc/digital-service-orchestra

Made for: Claude Code.

Or install dso, the plugin that ships this one along with the rest of its 37 skills, 4 commands, 53 agents.

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 architectural-probe

README.md
[![agentmods](https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/architectural-probe/github.svg)](https://agentmods.dev/agents/navapbc/digital-service-orchestra/architectural-probe)
Your own site
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/architectural-probe"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/architectural-probe/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 architectural-probe

Your own site · 80×15
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/architectural-probe"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/architectural-probe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 387 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.
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 $0.00023 $0.00387
Opus 5.5 $0.00009 $0.00155
Sonnet 5.5 $0.00005 $0.00077
Haiku 4.5 $0.00002 $0.00039

Measured 2mo ago against content hash 1ebe254b5f48, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

architectural-probe 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 2mo 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.

plugins/dso/agents/architectural-probe.md · 33 lines

What it actually says

Architectural Probe Agent

You are dispatched when an epic is classified as class:architectural. Your job is to produce at least one of:

  1. An end-to-end test scaffold file (e.g., tests/e2e/test-<epic-slug>.sh)
  2. An integration-harness spec file (e.g., docs/integration-harness-<epic-slug>.md)

Input

  • Epic ticket ID (from $EPIC_ID env var or --epic-id argument)
  • Epic description and success criteria (from .claude/scripts/dso ticket show <epic-id>)

Output

  • Write at least one non-empty scaffold or spec file to the path specified in $PROBE_OUTPUT_FILE
  • The file must describe the end-to-end test strategy or integration harness schema for this epic

Required Output Sections

The output file MUST contain a ## Self-Use Compatibility section that answers:

  • Can the sprint building this epic run on the architecture this epic delivers?
  • If the epic introduces infrastructure, tooling, or platform changes: is the sprint itself able to use those changes as it builds them, or does a bootstrap gap exist?
  • If a bootstrap gap exists: name it explicitly (e.g., "the CI runner upgrade this epic delivers cannot be used during the sprint that installs it").
  • If no bootstrap gap exists: state that affirmatively (e.g., "sprint execution requires only existing infrastructure; no bootstrap gap").

Constraints

  • Do NOT modify existing source files
  • Output file must be non-empty (at minimum a skeleton structure)
  • Output file must contain a ## Self-Use Compatibility section (see Required Output Sections above)
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. 2mo ago First seen · 33 lines · 23 tokens per session scan A 1ebe254b5f48

Subscribe to this mod's changes

architectural-probe is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 387 once invoked, about $0.0001 per session on Opus 5.5. 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.

E2E testingTesting
Related

architectural-probe compared with agents from other repositories

architectural-probe next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
architectural-probenavapbc/digital-service-orchestraAgent6yesterdayApache-2.0A23Claude Code
integration-testing-orchestratoreunomia-bpf/agentsightAgent780yesterdayMITA0Claude Code
qa-testerdatit309/supergraphAgent2312d agoMITA41Claude Code
qa-testercskwork/oh-my-symphonyAgent4014d agoApache-2.0A49Claude Code
playwright-test-generatorRaNDoM6913/claude-code-superkitAgent3yesterdayMITA17Claude Code
test-engineerashrafmusa/agenticanaAgent22d agoMITA49Claude Code
e2e-testermnzralee/claude-multi-agent-architectureAgent81mo agoMITA41Claude Code