compile-submission

compile-submission is a skill for Claude Code from runverdict/sf-security-review-toolkit. It costs 149 tokens per session (8,740 once invoked), scanned A, original, Apache-2.0.

A preparation step that assembles the documents and evidence needed for a Salesforce product-security review. It checks that required files exist, fills supported questionnaire answers, and compares those answers with the attached evidence.

In plain words
What is it for?
Use it after earlier security-review preparation steps and before submitting or paying for a review. It creates a readiness tracker, identifies gaps, and compiles the available submission materials.
Why use it?
It catches missing files, unsupported answers, and contradictions before the submission reaches Salesforce. Its result is preparation guidance, not a prediction that Salesforce will approve the package.

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 after earlier security-review preparation steps and before submitting or paying for a review. It creates a readiness tracker, identifies gaps, and compiles the available 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 compile-submission

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/compile-submission"><img src="https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/compile-submission.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,740 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 $0.00149 $0.08740
Opus 5 $0.00075 $0.04370
Sonnet 5 $0.00030 $0.01748
Haiku 4.5 $0.00015 $0.00874

Measured 10d ago against content hash 9e50aef2300e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

compile-submission 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 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.

Makes network callslowCapability

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

allowed-tools: Read Grep Glob Write Edit Bash(ls *) Bash(find *) Bash(cat *) Bash(curl *) Bash(git log *) Bash(git rev-parse *) Bash(mkdir *) Bash(cp *) Bash(tar *) Bash(node *harness/build-evidence-index.mjs *) Bash(nod
skills/compile-submission/SKILL.md · 545 lines

How it starts

The opening of the file, as written. The whole thing — 545 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compile Submission

Aggregate everything the prior phases produced into the submission package, verify each piece actually exists and holds together, and tell the operator plainly whether to submit. The three failure classes this phase kills: bouncing at the pre-queue materials check (a missing artifact or dead credential costs queue position without a reviewer ever being assigned — baseline: process-prequeue-validation), thin or undocumented-N/A answers that cost weeks of back-and-forth (baseline: fail-incomplete-questionnaire), and a questionnaire that contradicts its own attached artifacts — the contradiction reads as concealment and costs credibility on every other answer. The verdict this skill emits is preparation guidance, never a pass prediction — Salesforce runs its own penetration test regardless of anything submitted (baseline: dast-salesforce-runs-own-pentest).

When to use

  • The prior phases have state to compile (degrade gracefully: compile what exists, list what doesn't as TODO — the gaps ARE the output)
  • A go/no-go check before paying the review fee (paid per review; a remediated retest pays again — Returned and FP-only resubmits don't)
  • Re-compiling after remediation, a re-scan, or a scope change — the compile is cheap and idempotent; re-run it whenever upstream state moves
  • NOT for generating missing artifacts (route to /sf-security-review-toolkit:generate-artifacts or the owning phase), NOT for running scans (/sf-security-review-toolkit:run-scans), and NOT the submission itself — the wizard is operator-driven (baseline: process-submission-wizard)

Prerequisites

  • .security-review/scope-manifest.json — hard requirement; this skill refuses to compile without it (step 1)
  • Whatever exists of: .security-review/audit-ledger.json, artifacts in docs/security-review/, evidence in .security-review/evidence/, docs/security-review/test-environment.md
  • Templates: submission-checklist.md.tmpl, questionnaire.md.tmpl, readiness-tracker.md.tmpl in ${CLAUDE_PLUGIN_ROOT}/templates/
  • Token cost: trivial — this phase is a single-pass compile with no agent fan-out; the expensive phases are behind you

Read the full file on GitHub · 545 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 · 545 lines · 149 tokens per session scan A 9e50aef2300e

Subscribe to this mod's changes

compile-submission 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 149 tokens to every session and 8,740 once invoked, about $0.0007 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