reviewer-simulation

reviewer-simulation is a skill for Claude Code from runverdict/sf-security-review-toolkit. It costs 155 tokens per session (2,439 once invoked), scanned A, original, Apache-2.0.

A report that checks a Salesforce security-review preparation package from the viewpoint of a Salesforce product-security reviewer. It uses existing audit results, scan evidence, and scope information to show which review challenges are likely to be found or addressed.

In plain words
What is it for?
Use it after code audits and security scans, before compiling a Salesforce AppExchange review submission, and again after remediation. It produces a reviewer-focused report and a list of remaining challenges.
Why use it?
It helps partners see the security issues and documentation gaps a reviewer may notice before submission. It also shows whether fixes have changed the review status of individual findings.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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 code audits and security scans, before compiling a Salesforce AppExchange review submission, and again after remediation. It produces a reviewer-focused report and a list of remaining challenges.

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 reviewer-simulation

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/reviewer-simulation"><img src="https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/reviewer-simulation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,439 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 $0.00155 $0.02439
Opus 5 $0.00077 $0.01220
Sonnet 5 $0.00031 $0.00488
Haiku 4.5 $0.00015 $0.00244

Measured 10d ago against content hash d1ddd61f6115, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

reviewer-simulation 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 10d 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/reviewer-simulation/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer Simulation

Produce <target>/docs/security-review/reviewer-simulation.md: the submission seen through Salesforce Product Security's eyes. The deepest thing a partner wants is not "find my bugs" — it is "tell me what the reviewer is going to see." This skill answers that from data the toolkit already produced (the audit ledger, the scan evidence, the deployed-org audit if it ran), reframed and ranked by the reviewer's own order of attack so the partner fixes the headline first.

It introduces no new findings and no new requirement — it is a synthesis layer. Its honesty line is load-bearing: this is the toolkit's STATIC analysis framed as reviewer intent, not the reviewer's live penetration test (CONVENTIONS §2).

When to use

  • After /sf-security-review-toolkit:audit-codebase and ideally /sf-security-review-toolkit:run-scans — it reads their ledger + evidence
  • Before /sf-security-review-toolkit:compile-submission — the reviewer-sim report is a package artifact and its open-challenge list seeds the path-to-green
  • Re-run after remediation — a challenge flips WILL-FIND → ADDRESSED as the fix lands and the ledger entry moves to fixed
  • NOT a substitute for the audit (it finds nothing new) and NOT the pen test (Salesforce reproduces these live regardless)

Prerequisites

  • <target>/.security-review/scope-manifest.json — the elements filter the checklist (a TLS challenge for a package-only listing is N/A, never reported); refuse to run without it
  • <target>/.security-review/audit-ledger.json — the source of WILL-FIND / ADDRESSED verdicts; degrade gracefully if thin, but say plainly the simulation is weaker for it
  • ${CLAUDE_PLUGIN_ROOT}/methodology/reviewer-challenges.md — the challenge checklist (the data); read it, do not reinvent the tiers
  • Optionally the scan evidence under <target>/.security-review/evidence/ and the deployed-org audit report — they answer the scan-family and dynamic challenges

Steps

Read the full file on GitHub · 153 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. 10d ago First seen · 153 lines · 155 tokens per session scan A d1ddd61f6115

Subscribe to this mod's changes

reviewer-simulation 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 155 tokens to every session and 2,439 once invoked, about $0.0008 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.

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