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 commands/forcedotcom/sf-skills/plugin-recommendationsgit clone --depth 1 https://github.com/forcedotcom/sf-skillsWrote 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/commands/forcedotcom/sf-skills/plugin-recommendations)<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>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 | $0.00020 | $0.00439 |
| Opus 5 | $0.00010 | $0.00219 |
| Sonnet 5 | $0.00004 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
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.
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.
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.
- today First seen · 38 lines · 20 tokens per session scan A 5c2a5749f80e
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.
Other commands, from other repositories
project-recap
Generate a visual project recap for context switching.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
m-task-planner
Target: $ARGUMENTS (Default: requirement document(s) discovered in the project).
triage
Triage ServiceNow incidents — list open incidents, assess priority, investigate a specific INC, or analyze trends.
session-log
Create or append a session log entry.
my-tasks
Track, prioritize, and execute tasks with goal alignment and due date awareness. Claude doesn't just remind you — it helps get work done.