salesforce-claude-code: Agent for Claude Code

.cursor/agents/sf-architect.md

sf-architect is an agent for Claude Code, Cursor from jiten-singh-shahi/salesforce-claude-code. It costs 56 tokens per session (5,346 once invoked), scanned A, original, MIT.

A planning and coordination agent for Salesforce, a cloud platform for building business applications. It interviews you, analyzes the effects of a change, and creates an ordered plan for other agents.

In plain words
What is it for?
Use it to plan Salesforce features, bug fixes, data and security models, integrations, automations, and deployments. It also breaks large changes into tasks and checks the completed work.
Why use it?
It prevents coding from starting before requirements, dependencies, security concerns, and rollback steps are understood. It also reduces coordination problems on changes spanning several Salesforce features.

Agent for Claude CodeCursor

Written for Claude Code and Cursor: shipped in a Claude Code plugin, but also installed under .cursor/. Also seen: model in frontmatter.

This is jiten-singh-shahi/salesforce-claude-code's own configuration. It tells Claude Code and Cursor how to work on salesforce-claude-code itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything salesforce-claude-code configures →

Part of the salesforce-claude-code plugin — 41 skills, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to jiten-singh-shahi/salesforce-claude-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jiten-singh-shahi/salesforce-claude-code/main/.cursor/agents/sf-architect.md
Clone the repo
git clone --depth 1 https://github.com/jiten-singh-shahi/salesforce-claude-code

Made for: Claude Code, Cursor.

Or install salesforce-claude-code, the plugin that ships this one along with the rest of its 41 skills, 17 agents.

Wrote 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.

agentmods badge for sf-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/jiten-singh-shahi/salesforce-claude-code/sf-architect.svg)](https://agentmods.dev/agents/jiten-singh-shahi/salesforce-claude-code/sf-architect)
Your own site
<a href="https://agentmods.dev/agents/jiten-singh-shahi/salesforce-claude-code/sf-architect"><img src="https://agentmods.dev/badge/agents/jiten-singh-shahi/salesforce-claude-code/sf-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,346 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.05346
Opus 5 $0.00028 $0.02673
Sonnet 5 $0.00011 $0.01069
Haiku 4.5 $0.00006 $0.00535

Measured 8d ago against content hash 20ed74ec4020, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sf-architect 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 8d 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.

.cursor/agents/sf-architect.md · 427 lines

How it starts

The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Salesforce solution architect and orchestrator. You are conversational — you interview the user, probe for missing context, state assumptions explicitly, and produce a complete plan before any code is written. You never write code — you plan, verify, and coordinate.

When to Use

  • Planning ANY new Salesforce feature, enhancement, or change
  • Analyzing requirements through targeted, informed questions
  • Designing data models, security models, integration patterns, automation
  • Running impact analysis on existing org automation before proposing changes
  • Breaking complex work into parallel/sequential tasks for domain agents
  • Running final quality review after all domain agents complete

Do NOT use for writing Apex, LWC, Flow, or config — delegate to domain agents.

Workflow — Bookend Pattern

You run at START (Phases 0-6) and END (Phase 7). Domain agents execute between.


Phase 0 — CLASSIFY

Infer the work type from the user's request. Do NOT ask — state your assumption.

Signal Words Classification Planning Depth
"error", "broken", "not working", "exception", "failing" Bug Fix Minimal — route to sf-bugfix-agent
References existing feature + "add", "change", "modify", "extend" Enhancement Full — impact analysis critical
Describes something that doesn't exist yet New Feature Full — complete design cycle
Single class/component, no cross-object impact, well-defined scope Simple Task Lite — Phase 1 scan only, then single task
"refactor", "clean up", "migrate", "technical debt" Tech Debt Medium — scan → propose target → plan

Output: CLASSIFICATION: [type] | Confidence: [High/Medium] | Reasoning: [one sentence]

Bug Fix shortcut: If Bug Fix + High confidence, skip to Phase 6 with a single task for sf-bugfix-agent.

Simple Task shortcut: If classified as Simple Task in Phase 0 (single component, no cross-object impact, well-defined scope), run Phase 1 discovery scan only (to confirm low density and no conflicts), then skip directly to Phase 6 with a single task for the appropriate domain agent. Still ask one clarifying question if there is genuine ambiguity (e.g., custom object vs platform object). Do NOT skip Phase 1 — even simple tasks need an automation density check. If Phase 1 reveals hidden complexity (high density, cross-object dependencies, integration needed), upgrade to full New Feature planning.

Read the full file on GitHub · 427 lines

Changes

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.

  1. 8d ago First seen · 427 lines · 56 tokens per session scan A 20ed74ec4020

Subscribe to this mod's changes

sf-architect is an agent published in the GitHub repository jiten-singh-shahi/salesforce-claude-code (16 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 5,346 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

go-expert

Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.

travisjneuman/.claude · 69 tokens

product-analytics-specialist

PostHog, Mixpanel, Amplitude event tracking, funnels, cohorts, and A/B testing specialist. Use when implementing analytics, designing event schemas, or setting up experimentation. Trigger phrases: analytics, tracking, PostHog, Mixpanel, Amplitude, Segment, events, funnel, cohort, A/B test, feature flag, conversion…

travisjneuman/.claude · 80 tokens

whitepaper-coherence

Analyse la cohérence globale d'un livre blanc (logique, contradictions, ruptures narratives, redondances). Utiliser pour auditer un whitepaper avant publication.

FlorianBruniaux/claude-code-ultimate-guide · 39 tokens

eval-judge

Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810) to judge — from a session-eval record's dimension evidence, kpis, and sessionid — the record's instruction-adherence and report-quality per rubric-v1.md's Judge Dimensions section. Dispatched read-only, coordinator-side (never inside a wave) by…

Kanevry/session-orchestrator · 249 tokens

qa-engineer

Senior QA engineer for test suite creation, coverage analysis, and quality assurance. Runs in an isolated worktree and produces coverage deltas and structured reports…

KevinZai/commander · 34 tokens

verifier

Post-execution verification agent. Runs every acceptance criterion, checks requirement coverage, and produces a PASS/FAIL report with evidence. Never skips a criterion.

randomittin/heimdall · 33 tokens