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 Jaganpro/sf-skills --skill sf-permissionsgit clone --depth 1 https://github.com/Jaganpro/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/skills/jaganpro/sf-skills/sf-permissions)<a href="https://agentmods.dev/skills/jaganpro/sf-skills/sf-permissions"><img src="https://agentmods.dev/badge/skills/jaganpro/sf-skills/sf-permissions/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/jaganpro/sf-skills/sf-permissions"><img src="https://agentmods.dev/badge/skills/jaganpro/sf-skills/sf-permissions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00083 | $0.01251 |
| Opus 5 | $0.00042 | $0.00626 |
| Sonnet 5 | $0.00017 | $0.00250 |
| Haiku 4.5 | $0.00008 | $0.00125 |
Grade A, and why
sf-permissions 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 11d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sf-permissions
Use this skill when the user needs permission analysis and access auditing: Permission Set / Permission Set Group hierarchy views, “who has access to X?” investigations, user-permission analysis, or permission-set metadata review.
When This Skill Owns the Task
Use sf-permissions when the work involves:
- permission set / permission set group analysis
- user access investigation
- finding which permission grants object / field / Apex / flow / tab / custom-permission access
- auditing or exporting permission configuration
- reviewing permission metadata impacts
Delegate elsewhere when the user is:
- creating new metadata definitions → sf-metadata
- deploying permission sets → sf-deploy
- analyzing Apex-managed sharing logic → sf-apex
Required Context to Gather First
Ask for or infer:
- target org alias
- whether the question is about an object, field, Apex class, flow, tab, custom permission, or specific user
- whether the goal is hierarchy visualization, access detection, export, or metadata generation
- whether the output should be terminal-focused or documentation-friendly
Recommended Workflow
1. Classify the request
| Request shape | Default capability |
|---|---|
| “who has access to X?” | permission detector |
| “what does this user have?” | user analyzer |
| “show me the hierarchy” | hierarchy viewer |
| “export this permset” | exporter |
| “generate metadata from analysis” | generator or handoff |
2. Connect to the correct org
Verify sf auth before running permission analysis.
3. Use the narrowest useful query
Prefer focused analysis over broad org-wide scans unless the user explicitly wants a full audit.
When choosing identifiers, prefer stable metadata names first:
PermissionSet.NamePermissionSetGroup.DeveloperNameCustomPermission.DeveloperName- object and field API names such as
AccountorAccount.AnnualRevenue Assignee.Username/ email for user-centric checks
What ships with it
22 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.
- .gitignore 299 B
- CREDITS.md 2.1 KB
- LICENSE 1.0 KB
- README.md 2.4 KB
- references/agent-access-guide.md 3.8 KB
- references/permission-model.md 4.9 KB
- references/soql-reference.md 6.2 KB
- references/usage-examples.md 6.8 KB
- references/workflow-examples.md 2.4 KB
- requirements.txt 252 B
- scripts/__init__.py 320 B runs code
- scripts/auth.py 5.3 KB runs code
- scripts/cli.py 11 KB runs code
- scripts/hierarchy_viewer.py 11 KB runs code
- scripts/metadata_fetcher.py 11 KB runs code
- scripts/permission_detector.py 18 KB runs code
- scripts/permission_exporter.py 15 KB runs code
- scripts/renderers/__init__.py 333 B runs code
- scripts/renderers/ascii_tree.py 12 KB runs code
- scripts/renderers/mermaid.py 9.4 KB runs code
- scripts/tooling_api.py 9.8 KB runs code
- scripts/user_analyzer.py 12 KB runs code
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.
- 11d ago First seen · 151 lines · 83 tokens per session scan A 73b848204b77
sf-permissions is a skill published in the GitHub repository Jaganpro/sf-skills (423 stars, last pushed 4mo ago), licensed MIT. It adds 83 tokens to every session and 1,251 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…