continuous-agent-loop

continuous-agent-loop is a skill for Claude Code, Cursor from jiten-singh-shahi/salesforce-claude-code. It costs 43 tokens per session (2,385 once invoked), scanned A, original, MIT.

Design patterns for running coding agents repeatedly on Salesforce Apex and LWC projects, with checks between steps.

In plain words
What is it for?
Use them to build sequential pipelines, parallel agent workflows, CI/CD-style loops, RFC-based work breakdowns, and quality gates for tests, coverage, and governor limits.
Why use it?
They help structure ongoing automated development instead of treating each coding task as a single isolated run.

Skill for Claude CodeCursor

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

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

Install

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.

agentmods
npx agentmods add skills/jiten-singh-shahi/salesforce-claude-code/continuous-agent-loop
Any agent
npx skills add jiten-singh-shahi/salesforce-claude-code --skill continuous-agent-loop
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 continuous-agent-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/jiten-singh-shahi/salesforce-claude-code/continuous-agent-loop.svg)](https://agentmods.dev/skills/jiten-singh-shahi/salesforce-claude-code/continuous-agent-loop)
Your own site
<a href="https://agentmods.dev/skills/jiten-singh-shahi/salesforce-claude-code/continuous-agent-loop"><img src="https://agentmods.dev/badge/skills/jiten-singh-shahi/salesforce-claude-code/continuous-agent-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,385 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00043 $0.02385
Opus 5 $0.00022 $0.01192
Sonnet 5 $0.00009 $0.00477
Haiku 4.5 $0.00004 $0.00238

Measured 5d ago against content hash a3de1b86362d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

continuous-agent-loop 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.

.cursor/skills/continuous-agent-loop/SKILL.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Continuous Agent Loop

Patterns, architectures, and reference implementations for running Claude Code autonomously in loops on Salesforce projects. Covers sequential claude -p pipelines through RFC-driven multi-agent DAG orchestration with Apex test gates.

When to Use

  • Setting up autonomous Salesforce development workflows (Apex TDD cycles, LWC iteration)
  • Choosing the right loop architecture for your problem (simple deploy vs complex feature)
  • Building CI/CD-style continuous development pipelines with SF CLI gates
  • Running parallel agents for multi-layer Salesforce work (Apex + LWC + Integration)
  • Adding quality gates (governor limits, coverage thresholds) to autonomous workflows

Loop Selection Flow

Start
  |
  +-- Need strict CI/PR control? -- yes --> continuous-pr
  |
  +-- Need RFC decomposition? -- yes --> rfc-dag
  |
  +-- Need exploratory parallel generation? -- yes --> infinite
  |
  +-- default --> sequential

Loop Pattern Spectrum

Pattern Complexity Best For
Sequential Pipeline Low Daily Apex dev steps, scripted SFDX workflows
Infinite Agentic Loop Medium Parallel Apex/LWC generation from a spec
Continuous Claude PR Loop Medium Multi-day Apex TDD iterations with CI gates
De-Sloppify Pattern Add-on Quality cleanup after any Implementer step
Ralphinho / RFC-Driven DAG High Large Salesforce features with parallel units and merge queue

1. Sequential Pipeline

The simplest loop. Chain claude -p calls — each is a focused step with a clear prompt.

#!/bin/bash
set -e

# Step 1: Implement with TDD
claude -p "Read docs/order-service-spec.md. Implement OrderService.cls with TDD.
Target 85% coverage. No SOQL or DML inside for loops."

# Step 2: De-sloppify
claude -p "Review changes. Remove: unnecessary null checks, tests verifying platform
behavior, System.debug statements, commented-out code.
Run 'sf apex run test --class-names OrderServiceTest' after cleanup."

# Step 3: Verify
claude -p "Run 'sf project deploy start --dry-run --source-dir force-app/main/default/classes'.
Fix any failures. Do not add new features."

# Step 4: Commit
claude -p "Commit with message: feat: add order service with test coverage"

Read the full file on GitHub · 261 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. 5d ago First seen · 261 lines · 43 tokens per session scan A a3de1b86362d

Subscribe to this mod's changes

continuous-agent-loop is a skill published in the GitHub repository jiten-singh-shahi/salesforce-claude-code (15 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 2,385 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 2026-08-30.

Related

Other skills, from other repositories

sf-agentforce

Build, configure, and test Agentforce agents on Salesforce. Covers agent setup, topics, actions (Flow, Apex, PromptTemplate, External Service), Agent Scripts for deterministic FSM-based agents, PromptTemplate authoring, GenAI Models API, metadata structure, and agent testing via the Testing Center and CLI. Activate on…

Clientell-Ai/salesforce-skills · 111 tokens

sf-debug

Debug and troubleshoot Salesforce applications using debug logs, governor limit monitoring, error diagnosis, and performance profiling. Use when analyzing debug logs, diagnosing governor limit violations, interpreting stack traces, resolving common Salesforce errors, or profiling Apex performance. Activate on .log…

Clientell-Ai/salesforce-skills · 89 tokens

sf-diagram

Generate Mermaid diagrams from Salesforce metadata and architecture. Reads org metadata, Apex classes, Flow XML, and object definitions to produce ERDs, class diagrams, sequence diagrams, flow visualizations, and deployment dependency graphs. Activate on "diagram", "visualize", "ERD", "sequence diagram", "class…

Clientell-Ai/salesforce-skills · 97 tokens

sf-integration

Configure Salesforce integrations: Named Credentials, Connected Apps, External Services, Platform Events, CDC, and auth flows. Use when setting up integration infrastructure, metadata XML, or choosing architecture patterns. Activate on .namedCredential-meta.xml, .connectedApp-meta.xml, .platformEvent-meta.xml…

Clientell-Ai/salesforce-skills · 90 tokens

sf-omnistudio

Comprehensive OmniStudio / Salesforce Industries development skill covering OmniScripts, FlexCards, Integration Procedures, Data Mappers (DataRaptors), namespace detection, dependency mapping, and migration patterns. TRIGGER when: user works with OmniStudio components, asks about OmniScripts, FlexCards, Integration…

Clientell-Ai/salesforce-skills · 88 tokens

sf-permissions

Manage and audit Salesforce permissions: Permission Sets, Profiles, Permission Set Groups, object/field-level security (CRUD/FLS), custom permissions, and access troubleshooting. Use when asked about "who has access", permission set creation, FLS auditing, access errors, permission comparison, or muting permission…

Clientell-Ai/salesforce-skills · 111 tokens