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 delegated-administrationgit 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/delegated-administration)<a href="https://agentmods.dev/skills/banibratachatterjee/awesomesalesforceskills/delegated-administration"><img src="https://agentmods.dev/badge/skills/banibratachatterjee/awesomesalesforceskills/delegated-administration/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/delegated-administration"><img src="https://agentmods.dev/badge/skills/banibratachatterjee/awesomesalesforceskills/delegated-administration.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 | $0.00049 | $0.03039 |
| Opus 5 | $0.00024 | $0.01520 |
| Sonnet 5 | $0.00010 | $0.00608 |
| Haiku 4.5 | $0.00005 | $0.00304 |
Grade A, and why
delegated-administration 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 9d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegated Administration
This skill activates when you need to grant a non-System-Administrator user the ability to manage a scoped subset of users — including creating users, resetting passwords, assigning profiles and permission sets, or administering custom objects — without granting them full System Administrator access. It covers setup from scratch, review of existing configuration, and troubleshooting delegated admin permissions that are not working as expected.
Before Starting
Gather this context before working on anything in this domain:
- Confirm the org has a role hierarchy defined. Delegated admins can only manage users whose role is at or below their own role in the hierarchy. A delegated admin without a role, or whose role is not above the target users' roles, will not be able to manage those users.
- Identify which profiles the delegated admins should be permitted to assign. Only the specific profiles listed in the Delegated Administrator group can be assigned by that delegated admin; they cannot freely assign any profile in the org.
- Confirm whether custom object administration is required. Delegated admins can be given the ability to customize specific custom objects (fields, page layouts, validation rules), but this is configured separately from user management rights.
- Know the key limit: delegated admins cannot manage System Administrator users, regardless of role hierarchy position. This is a platform-enforced constraint.
Core Concepts
Delegated Administrator Groups
A Delegated Administrator group is the core configuration object. Each group has:
- Delegated Administrators — the users who receive the delegated admin rights.
- Users in Delegated Group — the set of users those admins can manage, defined by the roles those users hold.
- Assignable Profiles — the profiles the delegated admin can assign when creating or editing managed users.
- Assignable Permission Sets — (optional) specific permission sets the delegated admin can assign to managed users.
- Custom Object Administration — (optional) specific custom objects the delegated admin can customize.
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.
- 9d ago First seen · 221 lines · 49 tokens per session scan A 949bde932c36
delegated-administration is a skill published in the GitHub repository BanibrataChatterjee/AwesomeSalesforceSkills (3 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 3,039 once invoked, about $0.0002 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
v3-create-crud
A page generator for standard create, read, update, and delete screens, commonly called CRUD screens. It uses Element Plus, a Vue user-interface library, to build tables, searches, pagination, forms, and delete confirmations.
hunt-django
Hunt Django-specific vulnerabilities: DRF permission gaps, ORM injection, and admin exploitation.
v3-upsert-route
A route configuration helper for projects that keep their routes in `src/router/index.ts`. It creates or updates permanent and permission-controlled pages, including titles, icons, and child routes.
v3-use-composables
Documentation for reusable Vue functions in a project, covering device detection, asynchronous dropdown data, loading screens, pagination, routing, themes, page titles, and watermarks.
pro-upgrade
An upgrade guide for projects built with Ant Design Pro, a React-based application template for business software. It compares the project with the latest official template and merges framework updates while preserving application code.
v3-use-utils
Documentation for reusable utility functions in a project, including validation, date formatting, CSS variables, permissions, local storage, and tokens.