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.
/plugin marketplace add runverdict/sf-security-review-toolkit/plugin install sf-security-review-toolkitWrote 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.
[](https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/install-and-verify-package)<a href="https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/install-and-verify-package"><img src="https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/install-and-verify-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.
<a href="https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/install-and-verify-package"><img src="https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/install-and-verify-package.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00099 | $0.06374 |
| Opus 5 | $0.00049 | $0.03187 |
| Sonnet 5 | $0.00020 | $0.01275 |
| Haiku 4.5 | $0.00010 | $0.00637 |
Grade A, and why
install-and-verify-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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install and Verify Package
Adapted from the author's ISV-lifecycle tranche contributed to mvogelgesang/sf-mcp-partner-toolkit (Apache-2.0); see CREDITS.md.
Install the managed package into a clean throwaway org and verify every link in the chain headlessly — then audit the deployed artifact, which source reading alone cannot reach (install-time permission grants, registration collisions, credential resolution). This is what the Salesforce reviewer does when they install your package, previewed before submission. Each step below encodes a failure we hit on real subscriber installs.
Role in the autonomous deep audit
This is the core of the deployed-org deep audit — the step the whole CLI-gated path exists to reach. It is opt-in and CLI-gated: the orchestrator invokes it only when sf is authed and the operator opted into auditing the deployed package; the always-on source audit never depends on it. The common case is that the partner already has a released version, so the orchestrator hands its auto-resolved 04t… id straight here — the build step is skipped entirely.
- Consumes: a released
04t…package version id (auto-resolved by the orchestrator querying the Dev Hub for the package's released version, or produced by/sf-security-review-toolkit:build-managed-packagein the no-release-yet fallback), an authenticated target org from/sf-security-review-toolkit:bootstrap-cli-auth, and a clean throwaway org — a born-clean scratch org fromharness/standup-org.mjs(the default), or a template org cleaned by/sf-security-review-toolkit:teardown-mcp-registration.
When to use
- During the deployed-org deep audit, with a promoted (released) version on hand — the partner's existing release in the common case, or one produced by
/sf-security-review-toolkit:build-managed-packageonly when no release existed - When standing the package up in a clean throwaway org (a fresh scratch org or Trialforce template org) to audit the deployed artifact the way the reviewer will
- After every package upgrade, when re-auditing an upgraded release (see the upgrade runbook at the end)
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.
- 12d ago First seen · 279 lines · 99 tokens per session scan A a8b126bcba70
install-and-verify-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 99 tokens to every session and 6,374 once invoked, about $0.0005 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.
Other skills, from other repositories
ios-device-qa
Use when the user runs /ios-device-qa to drive a real iPhone over USB through a debug-bridge daemon and return a device QA report with verified interactions. Do not use for remote, credential, publish, deploy, or irreversible changes.
xcode-simulator-testing
Use when asked to run /xcode-simulator-testing with a scheme name or current to build and launch an iOS app in a simulator. Not for project regeneration: use ios-build-fix.
possible-worlds-qa
Use when a product surface must be tested against extreme or hostile worlds rather than collect green checks. Completeness mode classifies every world against stated criteria and reports gaps; break mode names an expected break signal per world, captures proof artifacts, and escalates worlds that survive. Not for…
run-smoke-tests
Use when asked to run smoke tests or verify a local build. Applies minimal fixes that unblock a stable passing result and reports flake risk honestly. Not for iterative bug fixing — use fix.
browser-testing
Test and debug browser code with Chrome DevTools MCP. Use when building or debugging browser UI, inspecting the DOM, capturing console errors, analyzing network requests, or verifying visual output.
visual-diff
Visual Regression Testing — screenshot comparison before and after changes. Use when user wants to check for visual regressions, compare UI changes, or verify CSS/layout changes didn't break anything.