generate-artifacts

generate-artifacts is a skill for Claude Code from runverdict/sf-security-review-toolkit. It costs 138 tokens per session (10,747 once invoked), scanned A, original, Apache-2.0.

A document-generation step for preparing Salesforce security-review materials from the actual code, configuration, and live server. It drafts items such as authentication and authorization flows, architecture and data-flow diagrams, data classifications, access controls, exposed tools, and OpenAPI documentation.

In plain words
What is it for?
Use it after code auditing finds no open critical or high-severity issues, or after an architecture change. It creates draft artifacts in the security-review documentation folder for an owner to check.
Why use it?
It keeps reviewer-facing documents tied to how the system is really built instead of how it was intended to work. Claims that cannot be verified from the code are marked as needing owner input.

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 code auditing finds no open critical or high-severity issues, or after an architecture change. It creates draft artifacts in the security-review documentation folder for an owner to check.

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 generate-artifacts

README.md
[![agentmods](https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/generate-artifacts.svg)](https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/generate-artifacts)
Your own site
<a href="https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/generate-artifacts"><img src="https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/generate-artifacts.svg" alt="Measured on agentmods" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,747 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 $0.00138 $0.10747
Opus 5 $0.00069 $0.05373
Sonnet 5 $0.00028 $0.02149
Haiku 4.5 $0.00014 $0.01075

Measured 8d ago against content hash 84d10331f726, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

generate-artifacts 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 8d 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: Task Read Grep Glob Write Write(**/.security-review/artifact-input.json) Bash(ls *) Bash(find *) Bash(cat *) Bash(git log *) Bash(git rev-parse *) Bash(curl *) Bash(node *harness/artifact-gate.mjs *) Bash(
skills/generate-artifacts/SKILL.md · 656 lines

How it starts

The opening of the file, as written. The whole thing — 656 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Artifacts

Draft every submission artifact that can be drafted from code into <target>/docs/security-review/, using the templates in ${CLAUDE_PLUGIN_ROOT}/templates/. The governing rule for this whole phase: generate from the as-built code, never from the design docs or memory. The reviewer reads these artifacts and then attacks exactly what they describe — a claim the live system contradicts costs more than an honestly documented gap, and the most common way partners produce such a claim is documenting what the system was intended to do. Every artifact is a draft for owner review; every claim is either traceable to code the generator actually read (path:line) or marked owner-input.

When to use

  • After /sf-security-review-toolkit:audit-codebase left no open critical/high findings — an AuthN/AuthZ doc written over an open auth finding documents the vulnerable flow for the reviewer
  • Refreshing artifacts after an architecture change, before a re-review, or when the consistency check (step 11) flagged drift
  • NOT for the questionnaire, checklist compilation, or readiness verdict (/sf-security-review-toolkit:compile-submission), NOT for scan evidence (/sf-security-review-toolkit:run-scans), and NOT for the test-environment runbook (/sf-security-review-toolkit:prepare-test-environment)

Prerequisites

  • <target>/.security-review/scope-manifest.json — refuse to run without it (artifact selection keys off the listing type); route to /sf-security-review-toolkit:scope-submission
  • Ideally <target>/.security-review/audit-ledger.json plus the latest audit report — the "strong controls observed" section feeds the control narratives and refuted entries seed the FP dossier. Degrade gracefully without them, but say plainly the drafts are thinner for it
  • For the live captures (step 3): a reachable server URL with its environment confirmed by the operator, same consent discipline as scope-submission
  • Templates in ${CLAUDE_PLUGIN_ROOT}/templates/ — this phase consumes submission-checklist.md.tmpl, authn-authz-flow.md.tmpl, data-flow-diagram.md.tmpl, data-sensitivity.md.tmpl, access-control.md.tmpl, exposed-tools-list.md.tmpl, mcp-server-details.md.tmpl, api-endpoints-spec.md.tmpl, fp-dossier.md.tmpl, and the WI-19 written-policy pack (incident-response-plan.md.tmpl, data-retention-deletion.md.tmpl, disaster-recovery-backup.md.tmpl, vulnerability-remediation-sla.md.tmpl, hosting-architecture.md.tmpl, prior-pentest-attestation.md.tmpl)

Read the full file on GitHub · 656 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. 8d ago First seen · 656 lines · 138 tokens per session scan A 84d10331f726

Subscribe to this mod's changes

generate-artifacts 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 138 tokens to every session and 10,747 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

sheet-music-publisher

Converts mastered audio to sheet music and creates printable songbooks. Use after mastering when the user wants sheet music or a songbook for their album.

bitwize-music-studio/claude-ai-music-skills · 36 tokens