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/compile-submission)<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.
<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>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 | $0.00149 | $0.08740 |
| Opus 5 | $0.00075 | $0.04370 |
| Sonnet 5 | $0.00030 | $0.01748 |
| Haiku 4.5 | $0.00015 | $0.00874 |
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 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-artifactsor 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 indocs/security-review/, evidence in.security-review/evidence/,docs/security-review/test-environment.md - Templates:
submission-checklist.md.tmpl,questionnaire.md.tmpl,readiness-tracker.md.tmplin${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
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.
- 10d ago First seen · 545 lines · 149 tokens per session scan A 9e50aef2300e
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.
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.
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.
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…
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…
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.
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.