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 instructions/ehebert7/salesforce-claude-framework/claude-mdgit clone --depth 1 https://github.com/ehebert7/salesforce-claude-frameworkWrote 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/instructions/ehebert7/salesforce-claude-framework/claude-md)<a href="https://agentmods.dev/instructions/ehebert7/salesforce-claude-framework/claude-md"><img src="https://agentmods.dev/badge/instructions/ehebert7/salesforce-claude-framework/claude-md.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 5.1 | $0.00369 | $0.00369 |
| Opus 5 | $0.00185 | $0.00185 |
| Sonnet 5 | $0.00074 | $0.00074 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
salesforce-claude-framework CLAUDE.md 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 5d 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.
What it actually says
Salesforce Project
Quick Commands
SFDX CLI
sf org login web --alias [alias]
sf project deploy start --source-dir force-app --target-org [alias]
sf project retrieve start --target-org [alias]
sf apex run test --target-org [alias] --code-coverage
sf org open --target-org [alias]
Local Development
npm run test:lwc
npm run lint
Project Structure
force-app/
├── main/
│ └── default/
│ ├── classes/
│ ├── triggers/
│ ├── lwc/
│ ├── flows/
│ ├── objects/
│ ├── permissionsets/
│ └── bots/
Architecture Patterns
Apex Layers
- Triggers → Call Handler classes only
- Handlers → Orchestrate Domain and Service calls
- Services → Business logic
- Selectors → All SOQL queries centralized
- Domains → Object-specific logic
Naming Conventions
- Triggers:
[Object]Trigger - Handlers:
[Object]TriggerHandler - Services:
[Feature]Service - Selectors:
[Object]Selector - Test Classes:
[ClassName]Test - LWC:
camelCase
Task Management
For large tasks, use /dev-docs to create implementation tracking docs in dev/active/[task-name]/.
Before ending a session, run /dev-docs-update to save progress.
Testing Requirements
- Minimum 85% code coverage
- All test methods must have System.assert
- Bulk test with 200+ records
- Test positive and negative scenarios
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.
- 5d ago First seen · 62 lines · 369 tokens per session scan A fc20da710203
salesforce-claude-framework CLAUDE.md is an instructions file published in the GitHub repository ehebert7/salesforce-claude-framework (11 stars, last pushed 9mo ago), licensed MIT. It adds 369 tokens to every session, about $0.0018 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 instructions, from other repositories
salesforce-metadata-mcp CLAUDE.md
Claude Code instructions for semwalajay83-sem/salesforce-metadata-mcp, covering salesforce-metadata-mcp — project context, what this is, critical rules, git is the source of truth and npm publish rules.
AwesomeSalesforceSkills CLAUDE.md
Claude Code instructions for PranavNagrecha/AwesomeSalesforceSkills, covering claude.md — salesforce skills repository, what this repo is, canonical rules, required workflow for skill creation or skill updates and repository structure.
AwesomeSalesforceSkills AGENTS.md
AGENTS.md instructions for PranavNagrecha/AwesomeSalesforceSkills, covering agents.md, before anything else: build the local index, rules every agent follows, what "generated" means, precisely and syncing: pick the right flag.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.