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/stay-listed)<a href="https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/stay-listed"><img src="https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/stay-listed/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/stay-listed"><img src="https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/stay-listed.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 | $0.00097 | $0.05075 |
| Opus 5 | $0.00048 | $0.02537 |
| Sonnet 5 | $0.00019 | $0.01015 |
| Haiku 4.5 | $0.00010 | $0.00507 |
Grade A, and why
stay-listed 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.
allowed-tools: Read Grep Glob Write Edit Bash(ls *) Bash(cat *) Bash(find *) Bash(curl *) Bash(git log *) Bash(git diff *) Bash(git tag *) Bash(sf *) AskUserQuestion How it starts
The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stay Listed
Turn the post-approval duties into a dated checklist and run it on a
schedule. Listings lapse quietly, and every lapse class has the same shape:
nothing breaks on the day it happens. The test org expires and nobody logs
in to notice; a platform mandate lands with a deadline and a delisting
consequence; three "minor" releases each sail through listing association
while their sum changes the architecture; the SSL Labs grade drops on a protocol
deprecation with zero code change — and the partner discovers all of it the
day Salesforce asks, which is the most expensive possible day. This skill
computes the next-due dates, runs what an agent can run, and puts the rest
in front of the operator with the deadline attached. The stake is the
listing itself: the mandate class carries delisting/suspension as its
published consequence (baseline: post-pkce-refresh-rotation-mandate).
When to use
- Immediately after approval: anchor the last-reviewed state and establish the cadence (step 2 — the anchor only exists if you set it now)
- On each recurrence — quarterly is the sensible default checkpoint given the annual re-review horizon (step 10 wires it)
- Before shipping ANY new version of a listed solution — the release gate (step 4)
- The moment a post-approval security finding lands — the ledger/incident interaction in step 5 has a 24-hour clock attached
- NOT for first-time review preparation — that is
/sf-security-review-toolkit:security-review-journey - NOT a substitute for the partner's own incident response or legal obligations — this skill schedules and surfaces; the partner remains the one accountable to Salesforce
Prerequisites
- An approved listing. The final submission state is the ideal input
(
docs/security-review/submission/readiness-tracker.md,docs/security-review/test-environment.md,.security-review/scope-manifest.json,.security-review/audit-ledger.json,.security-review/evidence/) — but degrade gracefully: a partner who was approved before adopting this toolkit has none of it, and step 1 reconstructs what is known and marks the gaps - The baseline at
${CLAUDE_PLUGIN_ROOT}/baseline/requirements-baseline.yaml— thepost-*entries drive this skill; read them at run time, never from this prose - Token cost: trivial — single-pass checks and probes, no agent fan-out.
The only expensive thing this skill ever recommends is a maintenance
/sf-security-review-toolkit:audit-codebasepass, and that runs cheap against a mature ledger
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.
- 11d ago First seen · 347 lines · 97 tokens per session scan A fc1317a925bd
stay-listed 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 97 tokens to every session and 5,075 once invoked, about $0.0005 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.