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 Clientell-Ai/salesforce-skills --skill sf-deploygit clone --depth 1 https://github.com/Clientell-Ai/salesforce-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/clientell-ai/salesforce-skills/sf-deploy)<a href="https://agentmods.dev/skills/clientell-ai/salesforce-skills/sf-deploy"><img src="https://agentmods.dev/badge/skills/clientell-ai/salesforce-skills/sf-deploy/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/clientell-ai/salesforce-skills/sf-deploy"><img src="https://agentmods.dev/badge/skills/clientell-ai/salesforce-skills/sf-deploy.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 | $0.00088 | $0.02184 |
| Opus 5 | $0.00044 | $0.01092 |
| Sonnet 5 | $0.00018 | $0.00437 |
| Haiku 4.5 | $0.00009 | $0.00218 |
Grade A, and why
sf-deploy 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 10d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deployment Orchestrator
You are a Salesforce deployment specialist. Manage multi-step deployments with error handling and dependency resolution.
Deployment Workflow
1. Pre-Deployment Checks
# Verify org connection
sf org display --target-org myOrg
# Check what will be deployed
sf project deploy preview -d force-app/
# Validate without deploying
sf project deploy start -d force-app/ --dry-run --target-org myOrg
2. Generate package.xml
# From org (full manifest)
sf project generate manifest --from-org myOrg --output-dir manifest/
# From local source
sf project generate manifest -d force-app/ --output-dir manifest/
3. Deployment Order (Dependencies First)
Deploy in this order to avoid dependency failures:
- Custom Objects & Fields — schema must exist before code references it
- Custom Labels & Custom Metadata — referenced by Apex and Flows
- Permission Sets & Custom Permissions — required by bypass logic
- Apex Classes — service classes, selectors, utilities first
- Apex Triggers — depend on handler classes
- Flows — may reference Apex actions
- LWC — may wire to Apex controllers
- Layouts, FlexiPages, Profiles — reference everything above
4. Deploy Commands
# Deploy specific directory
sf project deploy start -d force-app/main/default/classes/ --target-org myOrg
# Deploy with specific tests
sf project deploy start -d force-app/ --test-level RunSpecifiedTests --tests MyClassTest,MyOtherClassTest --target-org myOrg
# Deploy with all tests (production)
sf project deploy start -d force-app/ --test-level RunLocalTests --target-org myOrg
# Deploy specific metadata
sf project deploy start -m ApexClass:MyClass,ApexClass:MyClassTest --target-org myOrg
# Quick deploy (after successful validation)
sf project deploy quick --job-id <validationId> --target-org myOrg
5. Delta Deployments
For CI/CD, deploy only changed files:
# Using sfdx-git-delta
sfdx sgd:source:delta --from origin/main --to HEAD --output delta/
sf project deploy start -d delta/force-app/ --target-org myOrg
What ships with it
1 file 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.
- 10d ago First seen · 239 lines · 88 tokens per session scan A 31241ed24ca2
sf-deploy is a skill published in the GitHub repository Clientell-Ai/salesforce-skills (15 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 88 tokens to every session and 2,184 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
slo-define
Senior reliability engineer defining a service's reliability contract: choose SLIs, set an SLO target and measurement window, compute the error budget (100% minus the SLO), and write the error-budget policy (what happens when the budget is exhausted). Produces SLOSPEC.md. Activates when a service or critical user flow…
architecture-and-stack
Cloudflare-first platform selection. Decision trees for Workers, D1, R2, KV, DO, Queues, Vectorize, Containers, Sandboxes, Flagship, Agent Memory, Workflows v2. Default stack, override conditions, auth, data patterns, reliability.
modal-serverless-gpu
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
hugging-face-model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
hugging-face-cli
Execute Hugging Face Hub operations using the hf CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run compute jobs on HF infrastructure. Covers authentication, file transfers, repository creation, cache operations, and cloud compute.