prepare-test-environment

prepare-test-environment is a skill for Claude Code from runverdict/sf-security-review-toolkit. It costs 93 tokens per session (6,426 once invoked), scanned A, original, Apache-2.0.

A guided preparation runbook for the test environment used in a security review of a Salesforce agent integration. It covers the review organization, agent configuration, test users, external test tenant, and self-tests.

In plain words
What is it for?
Use it after security scans, before a re-review, or whenever the package, agent, tool descriptions, or review environment changes.
Why use it?
It helps ensure that an outside reviewer can actually test the submission in an isolated environment rather than encountering missing setup or unusable accounts.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the sf-security-review-toolkit plugin — 14 skills, 1 hook shipped together

Good fit Use it after security scans, before a re-review, or whenever the package, agent, tool descriptions, or review environment changes.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add runverdict/sf-security-review-toolkit
Claude Code
/plugin install sf-security-review-toolkit

Made for: Claude Code.

Or install sf-security-review-toolkit, the plugin that ships this one along with the rest of its 14 skills, 1 hook.

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 prepare-test-environment

README.md
[![agentmods](https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/prepare-test-environment/github.svg)](https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/prepare-test-environment)
Your own site
<a href="https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/prepare-test-environment"><img src="https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/prepare-test-environment/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 prepare-test-environment

Your own site · 80×15
<a href="https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/prepare-test-environment"><img src="https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/prepare-test-environment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,426 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00093 $0.06426
Opus 5 $0.00046 $0.03213
Sonnet 5 $0.00019 $0.01285
Haiku 4.5 $0.00009 $0.00643

Measured 9d ago against content hash f1822a5c529f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prepare-test-environment scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Read Write Edit Bash(sf *) Bash(export SF_AUTOUPDATE_DISABLE=true SF_DISABLE_AUTOUPDATE=true) Bash(curl *) Bash(ls *) Bash(cat *) AskUserQuestion
skills/prepare-test-environment/SKILL.md · 425 lines

How it starts

The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prepare Test Environment

Build and validate the environment the reviewer actually logs into. This is the guided-manual phase: org provisioning, agent wiring, and account creation are operator actions no tool can perform — but the generation work (utterance lists, probe scripts, runbook drafts) and the validation pass are automatable, and the validation pass is the entire point. An un-testable environment is a pure process failure that bounces the submission without a reviewer reading a line of code (baseline: fail-untestable-environment, process-prequeue-validation) — and unlike a code finding, it is 100% preventable from this side. Every step below encodes a way real submissions bounce.

When to use

  • After /sf-security-review-toolkit:run-scans — the endpoints the reviewer attacks here are the ones the DAST evidence already covered, in the same production-mode configuration
  • Re-validating before a re-review, after an org neared expiry, or after any change to the package, the agent, or the server's tool descriptions
  • NOT for the partner's dev environment — this is the reviewer-facing one, isolated and never production (baseline: testenv-external-test-instances)
  • NOT a substitute for the reviewer's own testing — Salesforce pen-tests the environment regardless of how thoroughly it was self-tested (baseline: dast-salesforce-runs-own-pentest)

Prerequisites

  • <target>/.security-review/scope-manifest.json (from /sf-security-review-toolkit:scope-submission) — which environment components apply. Missing? Offer to route there first; degraded mode walks every component and asks the operator which apply.
  • The access-control artifact's persona definitions (from /sf-security-review-toolkit:generate-artifacts) — the test users instantiate them. Missing? The personas can be defined inline here, but record that the access-control artifact must be reconciled afterward.
  • Partner Business Org / Environment Hub access for org creation (operator).
  • ${CLAUDE_PLUGIN_ROOT}/baseline/requirements-baseline.yaml readable.
  • Credentials never enter files this skill writes — locations and labels only (CONVENTIONS §6).

Read the full file on GitHub · 425 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. 9d ago First seen · 425 lines · 93 tokens per session scan A f1822a5c529f

Subscribe to this mod's changes

prepare-test-environment is a skill published in the GitHub repository runverdict/sf-security-review-toolkit (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 93 tokens to every session and 6,426 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.