plugin-recommendations

plugin-recommendations is a command for coding agents from forcedotcom/sf-skills. It costs 20 tokens per session (439 once invoked), scanned A, original, Apache-2.0.

A settings command for controlling how readily this plugin recommends uninstalled Salesforce plugins that may match your task. It supports off, named sensitivity levels, and a custom threshold.

In plain words
What is it for?
Turning plugin recommendations off, choosing low, standard, or high sensitivity, setting a custom threshold, and viewing the current setting.
Why use it?
It lets you reduce unwanted recommendations or make the plugin suggest possible add-ons more often. The numeric setting can be unintuitive because lower values trigger more readily.

Command

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

Install

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.

agentmods
npx agentmods add commands/forcedotcom/sf-skills/plugin-recommendations
Clone the repo
git clone --depth 1 https://github.com/forcedotcom/sf-skills

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 plugin-recommendations

README.md
[![agentmods](https://agentmods.dev/badge/commands/forcedotcom/sf-skills/plugin-recommendations.svg)](https://agentmods.dev/commands/forcedotcom/sf-skills/plugin-recommendations)
Your own site
<a href="https://agentmods.dev/commands/forcedotcom/sf-skills/plugin-recommendations"><img src="https://agentmods.dev/badge/commands/forcedotcom/sf-skills/plugin-recommendations.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 439 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00020 $0.00439
Opus 5 $0.00010 $0.00219
Sonnet 5 $0.00004 $0.00088
Haiku 4.5 $0.00002 $0.00044

Measured today against content hash 5c2a5749f80e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plugin-recommendations 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 today.

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.

plugins/builder/salesforce-development/commands/plugin-recommendations.md · 38 lines

What it actually says

Manage this plugin's uninstalled-plugin recommendation sensitivity — how readily it proposes an uninstalled Salesforce plugin that matches your task. Default is standard; off is a true hard-off (no recommendation on any surface: SessionStart, prompt submission, the bypass gate, or the discovery command) and honors SF_DISABLE_PLUGIN_MATCH.

Named levels, from least to most readily triggered: off, low (threshold 6.0), standard (threshold 3.5, default), high (threshold 3.0). high sensitivity needs the least evidence before proposing a plugin, low needs the most — same relationship as a smoke detector's sensitivity dial.

A custom number from 1.0 to 10.0 is also accepted for finer control, on that same threshold scale: it is compared directly against the match score, so a lower number triggers more readily (more sensitive) and a higher number triggers less readily (less sensitive, more evidence required). It is easy to get this backwards — "high" sensitivity is the low end of the number range (3.0), not the high end.

If the user asked to turn it off:

${CLAUDE_PLUGIN_ROOT}/scripts/sf-context plugin-match-config off

If the user asked to turn it on (reset to the plugin's default):

${CLAUDE_PLUGIN_ROOT}/scripts/sf-context plugin-match-config on

If the user asked to set a level or custom number (e.g. low, high, or 7.5):

${CLAUDE_PLUGIN_ROOT}/scripts/sf-context plugin-match-config set <value>

Otherwise show current status:

${CLAUDE_PLUGIN_ROOT}/scripts/sf-context plugin-match-config status

Output the result verbatim to the user.

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. today First seen · 38 lines · 20 tokens per session scan A 5c2a5749f80e

Subscribe to this mod's changes

plugin-recommendations is a command published in the GitHub repository forcedotcom/sf-skills (961 stars, last pushed yesterday), licensed Apache-2.0. It adds 20 tokens to every session and 439 once invoked, about $0.0001 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 2026-09-03.