Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/runverdict/sf-security-review-toolkit/bootstrap-cli-authnpx skills add runverdict/sf-security-review-toolkit --skill bootstrap-cli-authgit clone --depth 1 https://github.com/runverdict/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/bootstrap-cli-auth)<a href="https://agentmods.dev/skills/runverdict/sf-security-review-toolkit/bootstrap-cli-auth"><img src="https://agentmods.dev/badge/skills/runverdict/sf-security-review-toolkit/bootstrap-cli-auth.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.05003 |
| Opus 5 | $0.00034 | $0.02501 |
| Sonnet 5 | $0.00014 | $0.01001 |
| Haiku 4.5 | $0.00007 | $0.00500 |
Grade A, and why
bootstrap-cli-auth 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap CLI Auth
Adapted from the author's ISV-lifecycle tranche contributed to mvogelgesang/sf-mcp-partner-toolkit (Apache-2.0); see CREDITS.md.
Build a working Salesforce CLI environment from a bare machine and authenticate the org fleet the deployed-org deep audit touches — the Dev Hub, the namespace holder (only if a version still has to be built), and the throwaway scratch/trial orgs the package is stood up in. Headless throughout: this is the auth foundation for installing the partner's existing package version into a clean org and auditing the deployed artifact.
Role in the autonomous deep audit
This is an opt-in, CLI-gated step. The autonomous orchestrator invokes it only when both are true: sf is authed (or the operator agrees to install + auth it here), and the operator opted into the deployed-org deep audit (the ✦ OPTIONAL POWER-UP the preflight offers when it senses an sf install). The always-on core — the read-only source audit — never reaches this skill; nothing here is required to produce a readiness verdict from source alone.
- Consumes: nothing from a prior step — it detects bare-machine state and builds from it. If the orchestrator has already resolved a released
04t…package version id (by querying the Dev Hub for the package's released version), it carries through as context for what gets installed downstream; this skill only needs the org fleet authed.
When to use
- On a fresh machine — CI runner, remote server, devcontainer, cloud IDE — where
sfis not installed or no org is authenticated, and the operator has opted into the deployed-org deep audit - When the preflight sensed no
sfauth and offered to install + authenticate it so the deployed package can be audited - When the deep audit needs more than one org (Dev Hub plus a throwaway test org, and a namespace holder only if a version must still be built) and you want a clean alias scheme before standing the package up
- NOT for the always-on source audit — that read-only core never reaches this skill; nothing here is required to produce a readiness verdict from source alone
- NOT for scaffolding or authoring an MCP integration from scratch — that à-la-carte path lives in the sibling sf-mcp-partner-toolkit, not here
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.
- 4d ago First seen · 242 lines · 69 tokens per session scan A 551de26561e4
bootstrap-cli-auth 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 69 tokens to every session and 5,003 once invoked, about $0.0003 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.
Other skills, from other repositories
researcher
Conducts investigative-grade research with primary source analysis, cross-verification, and trial-level depth. Use when an album needs factual research, source material, or verification of claims.
pronunciation-specialist
Scans lyrics for pronunciation risks and prevents Suno mispronunciations. Use when writing lyrics with proper nouns, technical terms, homographs, or non-English words.
researchers-primary-source
Researches the subject's own words from tweets, blogs, forums, and chat logs. Use when research needs direct quotes or first-person accounts.
researchers-tech
Researches project histories, changelogs, developer interviews, and open source documentation. Use when the album subject involves technology projects or developer stories.
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.
promote-idea
Converts an album idea from IDEAS.md into an actual album project in one step. Use when the user says "promote [idea title]", "turn idea into album", or "start working on [idea]".