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 skills add BanibrataChatterjee/AwesomeSalesforceSkills --skill assignment-rulesgit clone --depth 1 https://github.com/BanibrataChatterjee/AwesomeSalesforceSkillsWrote 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/banibratachatterjee/awesomesalesforceskills/assignment-rules)<a href="https://agentmods.dev/skills/banibratachatterjee/awesomesalesforceskills/assignment-rules"><img src="https://agentmods.dev/badge/skills/banibratachatterjee/awesomesalesforceskills/assignment-rules/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/banibratachatterjee/awesomesalesforceskills/assignment-rules"><img src="https://agentmods.dev/badge/skills/banibratachatterjee/awesomesalesforceskills/assignment-rules.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 | $0.00106 | $0.03135 |
| Opus 5 | $0.00053 | $0.01568 |
| Sonnet 5 | $0.00021 | $0.00627 |
| Haiku 4.5 | $0.00011 | $0.00314 |
Grade A, and why
assignment-rules 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 7d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assignment Rules
This skill activates when an admin needs to create, configure, audit, or troubleshoot Lead or Case assignment rules — including rule entry criteria, queue vs user assignment, API-triggered rule evaluation, and round-robin patterns with Apex when native distribution is insufficient.
Before Starting
Gather this context before working on assignment rules:
- Which object? Assignment rules only exist for Lead and Case. Other objects do not have native assignment rules — use Flow or Apex for those.
- Is there already an active rule? Only one assignment rule can be active per object at a time. Activating a new rule deactivates the previous one automatically.
- How will records be created? Web-to-Lead, Web-to-Case, and Email-to-Case automatically trigger the active assignment rule. UI-created records require the user to check "Assign using active assignment rule." API-created records require an explicit header.
- Are queues needed? Queues allow a pool of users to work records collaboratively. Assignment rules can route to a queue instead of a single user. Understand who should own the record before designing criteria.
Core Concepts
Active Rule Limit and Rule Entry Order
Salesforce enforces a hard limit of one active assignment rule per object (Lead and Case each). When you activate a new rule, the previously active rule is automatically deactivated. You cannot have two active rules simultaneously.
Each assignment rule contains multiple rule entries. Rule entries are evaluated in order — the first entry whose criteria match the incoming record wins, and Salesforce assigns the record to that entry's target. Evaluation stops immediately after the first match. No subsequent entries are evaluated.
This first-match-wins behavior means entry order is critical. More specific criteria should appear earlier in the list than broad catch-all entries.
A rule can have up to 3,000 rule entries. Each entry specifies:
- Filter criteria (field conditions using standard AND/OR logic)
- Assignment target: a User or a Queue
- An optional email template to send the assigned user or queue a notification
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 238 lines · 106 tokens per session scan A b74da4164981
assignment-rules is a skill published in the GitHub repository BanibrataChatterjee/AwesomeSalesforceSkills (3 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 106 tokens to every session and 3,135 once invoked, about $0.0005 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 skills, from other repositories
assignment-rules
Use this skill when configuring or troubleshooting Lead or Case assignment rules in Salesforce: creating rule entries, setting filter criteria, assigning records to users or queues, understanding when rules run, and implementing round-robin patterns with Apex. Trigger keywords: lead assignment, case assignment…
lead-routing
Intelligent lead assignment and routing - AI-powered scoring, territory mapping, round-robin distribution, and workload balancing.
approval-processes
Design, review, or troubleshoot Salesforce Approval Processes. Triggers: 'submit for approval', 'approver', 'record locked', 'recall approval', 'approval step', 'discount approval'. NOT for submitting or acting on approvals from Apex - use admin/approval-process-apex-patterns. NOT for CPQ Advanced Approvals (SBAA…
integration-rule-engine
A declarative routing engine that turns ticket / error attributes (reporter, label, project, area path, error class, environment) into a tag + AI agent + priority assignment, so cross-source workflows ("security tickets always go to the OWASP reviewer") stay out of code and in user-editable rules.
pipefy-building
Thin router for Pipefy build and configure asks: map user intent to the correct domain skill (pipes, automations, AI agents, iPaaS, portals, etc.). Use when the user wants to create, build, configure, or integrate something in Pipefy and you need to know which skill to open. Do not use this skill as a delivery…
sales-expert
Build comprehensive sales technology solutions including CRM implementation, pipeline management, sales forecasting, and performance analytics. Use when the user mentions CRM, sales pipelines, lead qualification, opportunity tracking, sales forecasting, quotas or territories, or sales automation.