security-review-journey

security-review-journey is a skill for Claude Code from runverdict/sf-security-review-toolkit. It costs 183 tokens per session (17,219 once invoked), scanned A, original, Apache-2.0.

A guided process for preparing Salesforce AppExchange or AgentExchange software for a security-review submission. It checks the project, runs supported reviews, collects evidence, and builds a submission package while recording approval points.

In plain words
What is it for?
Use it to prepare a Salesforce package for security review, inspect its architecture and source, run permitted scans and audits, gather artifacts, and produce submission materials.
Why use it?
It organizes a review that otherwise requires many separate checks, documents, scans, and decisions. It also identifies limits and known blockers without promising approval.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Claude Code.

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 to prepare a Salesforce package for security review, inspect its architecture and source, run permitted scans and audits, gather artifacts, and produce submission materials.

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 security-review-journey

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/security-review-journey"><img src="https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/security-review-journey.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 183 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 17,219 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 $0.00183 $0.17219
Opus 5 $0.00092 $0.08610
Sonnet 5 $0.00037 $0.03444
Haiku 4.5 $0.00018 $0.01722

Measured 11d ago against content hash dbfb73c306ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

security-review-journey 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 11d 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.

outer tool call, so its pip/curl/git/npm subprocesses run unprompted under it),
skills/security-review-journey/SKILL.md · 930 lines

How it starts

The opening of the file, as written. The whole thing — 930 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Review Journey

The autonomous driver for the AppExchange/AgentExchange security-review submission. One trigger phrase runs a seconds-long preflight, surfaces a single 3-tier report, then drives every phase to a finished, downloadable submission package — pausing only when an input would actually degrade the audit, or when an action reaches outside read-only-local: touching something live (a read-only probe, a scratch org) OR mutating the host / egressing to the network (installing a scanner, fetching third-party rule packs). Those all need explicit consent — silence-is-yes / full-auto authorizes ONLY the inputs the preflight already DETECTED (elements, endpoints, package facts, resume state), never an install, a network fetch, a live op, the consent gates, or the audit-phase stops (the tier go-ahead and the show-the-target-map step) — every one of those is asked via AskUserQuestion and recorded. It never says "will pass": the strongest verdict it can reach is "first-attempt- ready / no known blockers in what we can verify — Salesforce pen-tests regardless." It is read-only on the partner's source, and never installs software or fetches remote content without a yes (see run-scans' hard boundary; an absent scanner is PENDING-OWNER-RUN, not an auto-install).

This is a deliberate change from the 0.1 router: that version only detected state and handed off. This one drives. It still answers "just this step" and "where are we?" as a router when that's all you asked — but the default for a run-shaped request is to run.

When to use

  • Run it all: "run the security review", "prep my app for the Salesforce review", "get me ready to submit to AppExchange / AgentExchange". → full autonomous run.
  • Readiness question: "am I ready for AppExchange/AgentExchange?" → preflight
    • run (the honest answer requires the audit, not just a checklist glance).
  • Resume: "continue the review", "pick up where we left off" → preflight detects the furthest-complete phase and resumes from there.
  • Status only: "where are we on the review?", "what's left?" → router mode: report state and the single next action, run nothing.
  • One step: "just run the audit", "regenerate the artifacts" → router mode: hand to that one skill and stop.
  • NOT a general application security review. This skill is scoped to the Salesforce ISV security-review submission — its findings, artifacts, and verdict are shaped to that review's eight categories and five-step wizard. A bare "is my app secure?" with no AppExchange/AgentExchange intent is out of scope; say so and offer the scoped run rather than hijacking the request.
  • NOT a substitute for Salesforce's own penetration test, and NOT a certifier — it prepares evidence and gets you close, for free, before the fee.

Read the full file on GitHub · 930 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. 11d ago First seen · 930 lines · 183 tokens per session scan A dbfb73c306ef

Subscribe to this mod's changes

security-review-journey 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 183 tokens to every session and 17,219 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

explicit-checker

Scans lyrics for explicit content and verifies that explicit flags match actual content. Use before Suno generation or release to ensure accurate content ratings.

bitwize-music-studio/claude-ai-music-skills · 32 tokens

plagiarism-checker

Scans lyrics for phrases that may match existing songs using web search and LLM knowledge. Use before release to check for unintentional borrowing.

bitwize-music-studio/claude-ai-music-skills · 35 tokens

compliance-analysis

Guides Slice MCP compliance analysis using compliance ticket breakdowns and object-level compliance tickets, plus related stakeholder, securities, equity plan, equity pool, valuation, tax-treatment, and cap-table tools. Use when answering questions about company compliance posture, compliance tickets, missing data…

Global-Slice/claude-plugin · 98 tokens

equity-compensation-analysis

Guides Slice MCP analysis of equity compensation, grants, options, RSUs, vesting, exercises, forfeitures, PTEP, tax treatments, and valuations. Use when answering questions about employee equity, grant positions, vested or exercisable quantities, exercise price, FMV/409A, option pool consumption, tax treatment, or…

Global-Slice/claude-plugin · 78 tokens

negotiation

Danish consumer rights, negotiation tactics, email templates, and pricing benchmarks for subscription price negotiation. Reference this when drafting negotiation emails or advising on subscription costs.

peerjakobsen/smartspender · 35 tokens

validate-album

Validates album directory structure, file locations, and content integrity. Use before release or whenever the user wants to check an album's structural health.

bitwize-music-studio/claude-ai-music-skills · 33 tokens