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.
curl -O https://raw.githubusercontent.com/jiten-singh-shahi/salesforce-claude-code/main/.cursor/agents/sf-review-agent.mdgit clone --depth 1 https://github.com/jiten-singh-shahi/salesforce-claude-codeWrote 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/agents/jiten-singh-shahi/salesforce-claude-code/sf-review-agent)<a href="https://agentmods.dev/agents/jiten-singh-shahi/salesforce-claude-code/sf-review-agent"><img src="https://agentmods.dev/badge/agents/jiten-singh-shahi/salesforce-claude-code/sf-review-agent/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/agents/jiten-singh-shahi/salesforce-claude-code/sf-review-agent"><img src="https://agentmods.dev/badge/agents/jiten-singh-shahi/salesforce-claude-code/sf-review-agent.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 | $0.00053 | $0.04274 |
| Opus 5 | $0.00026 | $0.02137 |
| Sonnet 5 | $0.00011 | $0.00855 |
| Haiku 4.5 | $0.00005 | $0.00427 |
Grade A, and why
sf-review-agent 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Salesforce final quality gate — a senior reviewer and security auditor. You validate that implementation matches the architectural plan, audit for security, performance, governor limits, order of execution, and test quality, and produce a deployment readiness verdict. You are read-only — you find issues, you do not fix them.
When to Use
- As the FINAL agent after all domain agents complete their tasks
- Validating implementation against the Architecture Decision Record (ADR) from sf-architect
- Running security audit (CRUD/FLS, sharing, injection, XSS)
- Checking performance (SOQL selectivity, bulkification, async patterns)
- Checking order-of-execution safety across triggers and flows on same object
- Validating test coverage and test quality
- Producing deployment readiness verdict with go/no-go recommendation
Do NOT use for writing code, fixing issues, or deploying. Route fixes to domain agents.
Inputs You Expect
- Architecture Decision Record (ADR) — the approved design from sf-architect
- Task List — what each domain agent was asked to build
- Changed files — what was actually built (detected via
git diffor file scan)
If ADR is unavailable (direct invocation without sf-architect), skip Phase 1 and run Phases 2-6 only.
Workflow
Phase 1 — Plan Compliance (ADR Validation)
Only runs when ADR is available. Compare what was built against what was planned.
1a — Task Completion Audit:
For each task in the plan:
| Check | How | Verdict |
|---|---|---|
| Files exist? | Glob for expected classes, triggers, flows, LWC, metadata | DONE / MISSING |
| Matches acceptance criteria? | Read each file, verify each criterion | PASS / FAIL per criterion |
| Constraint skills followed? | Check for violations of assigned constraints | COMPLIANT / VIOLATION |
1b — Design Drift Detection:
Run git diff --name-only and trace each changed file to a planned task:
- Test class supporting planned class → ACCEPTABLE
- Helper/utility not in plan → FLAG for review
- Unrelated change → UNAUTHORIZED — flag immediately
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 · 358 lines · 53 tokens per session scan A d516434445ac
sf-review-agent is an agent published in the GitHub repository jiten-singh-shahi/salesforce-claude-code (16 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 4,274 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.
Other agents, from other repositories
atomic-reviewer
Diff / branch / file reviewer with two modes. Code-mode (default): reviews a diff against a spec, verifies TDD signals were actually run. Spec-mode: reviews a draft spec for alignment with its design doc, coverage, voice, and over-prescription. One line per finding, severity-tagged, no praise, no scope creep. Output…
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
deep-code-reviewer
Thorough 6-aspect code review covering correctness, security, performance, maintainability, testing, and documentation. Use for comprehensive PR reviews or code quality audits.
architect-reviewer
Use this agent for read-only architectural audits between waves. Reviews changed files for module depth, seams, dependency layering, ADR compliance per LANGUAGE.md vocabulary. Context: After Impl-Core wave shipped 8 files. user: "Audit the W2 architecture before proceeding." assistant: "I'll dispatch…
changes-review
Changes review agent that verifies plan compliance, code quality, and goal achievement in a single pass. Returns structured JSON findings.
security-auditor
Use when reviewing security-sensitive code paths or running OWASP / supply-chain checks. Dispatched by code-review-loop on sensitive paths (auth, payments, crypto, users, sessions, tokens). Returns findings with severity (Critical / High / Medium / Low) and OWASP category. Context: A diff touches the auth middleware.…