build-managed-package

build-managed-package is a skill for Claude Code from runverdict/sf-security-review-toolkit. It costs 113 tokens per session (5,684 once invoked), scanned A, original, Apache-2.0.

A fallback build process that creates a released Salesforce managed 2GP package from source code when no released version exists. A managed 2GP is an installable Salesforce package whose code is controlled by its publisher.

In plain words
What is it for?
Use it during a Salesforce security audit when Dev Hub has no released package version. It creates packaging files, a post-install handler, a CSP Trusted Site, and updates the Salesforce project configuration.
Why use it?
It provides an installable package for the security audit when there is no existing release to test. It avoids rebuilding a package when a released version is already available.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: 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 during a Salesforce security audit when Dev Hub has no released package version. It creates packaging files, a post-install handler, a CSP Trusted Site, and updates the Salesforce project configuration.

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 build-managed-package

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/build-managed-package"><img src="https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/build-managed-package.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,684 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 $0.00113 $0.05684
Opus 5 $0.00056 $0.02842
Sonnet 5 $0.00023 $0.01137
Haiku 4.5 $0.00011 $0.00568

Measured 9d ago against content hash 47e71fc53de2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

build-managed-package 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 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.

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.

skills/build-managed-package/SKILL.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Managed Package

Adapted from the author's ISV-lifecycle tranche contributed to mvogelgesang/sf-mcp-partner-toolkit (Apache-2.0); see CREDITS.md.

Promote the four MCP metadata components (plus a post-install handler and a CSP Trusted Site) into a released managed 2GP. Every step below encodes a packaging failure we hit on the way to a released version — the order matters.

This skill is not blanket read-only: it does not touch the partner's application logic, but it does generate packaging scaffolding into force-app/ (the MCPPostInstall handler and a CspTrustedSite) and edit sfdx-project.json — and it does so only on the no-existing-release path, when there is no released version to audit and one has to be cut.

Role in the autonomous deep audit

This is the build-only-if-needed step of the deployed-org deep audit. The common case is the opposite: the partner is prepping a package they have already released, so the orchestrator skips this entirely and goes straight to standing up the existing 04t… version. This skill runs only when the sf auto-resolution (the orchestrator querying the Dev Hub for the package's released version) finds nothing — sf package version list shows no row with IsReleased = true for this package — yet the operator opted into the deployed-org deep audit and there is source to package. It is opt-in and CLI-gated like the rest of the deep audit: never part of the always-on source audit, never invoked unless sf is authed.

  • Consumes: an authenticated devhub + ns-holder fleet from /sf-security-review-toolkit:bootstrap-cli-auth, and the partner's integration metadata in force-app/main/default/. The orchestrator routes here only after auto-resolution confirms no released version exists.
  • Feeds: a promoted (released) 04t… package version id that /sf-security-review-toolkit:install-and-verify-package stands up in the throwaway org for the deployed-artifact audit.

When to use

Read the full file on GitHub · 255 lines

Files

What ships with it

2 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.

  1. 9d ago First seen · 255 lines · 113 tokens per session scan A 47e71fc53de2

Subscribe to this mod's changes

build-managed-package 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 113 tokens to every session and 5,684 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 2026-08-31.