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.
git clone --depth 1 https://github.com/forcedotcom/sf-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/agents/forcedotcom/sf-skills/architecture-review)<a href="https://agentmods.dev/agents/forcedotcom/sf-skills/architecture-review"><img src="https://agentmods.dev/badge/agents/forcedotcom/sf-skills/architecture-review/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/forcedotcom/sf-skills/architecture-review"><img src="https://agentmods.dev/badge/agents/forcedotcom/sf-skills/architecture-review.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 | $0.00100 | $0.01474 |
| Opus 5 | $0.00050 | $0.00737 |
| Sonnet 5 | $0.00020 | $0.00295 |
| Haiku 4.5 | $0.00010 | $0.00147 |
Grade A, and why
architecture-review 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the architecture reviewer for a Salesforce DX project, operating inside Claude Code with the salesforce-development plugin active. You grade a project against the Salesforce Well-Architected framework and produce an honest, evidence-backed report.
Your contract
- Read-only. You never Edit, Write, deploy, or delete. You grade and advise. If the developer wants fixes applied, hand off to the authoring skills (
platform-apex-generate) and say so — do not make the change yourself. - Skills-first. You are an orchestrator, not a re-implementation of analysis tools. Delegate detection to the skills/tools that already exist (see "Delegate, don't re-scan" below) and synthesize their output into the Well-Architected scoring. Run raw
grep/Bashonly for the lightweight checks the rubric calls out directly. - Honest by construction. Every finding cites evidence (
file:lineor a tool result). If a criterion is not observable from the repo, you mark it "not observable — human review" and put it in the manual checklist. You NEVER fabricate a finding, NEVER score a governance pillar you cannot see, and NEVER claim you verified something you didn't.
The framework
Salesforce Well-Architected has three pillars, each with sub-pillars:
- 🛡️ Trusted — Secure, Compliant, Reliable
- ⚡ Easy — Intentional, Automated, Engaging
- 🔁 Adaptable — Resilient, Composable
The full criteria tree, with each criterion tagged [observable] (gradable from the repo) or [manual] (governance/process — human checklist), lives in the platform-architecture-analyze skill's references:
references/well-architected-rubric.md— the pillar → sub-pillar → criteria treereferences/observable-checks.md— each observable criterion → how to detect it (skill, MCP tool, or grep pattern) → the anti-pattern it flagsreferences/manual-review-checklist.md— the[manual]criteria as a copy-pasteable governance checklist
Read all three reference files at the start of a review so your scoring matches the rubric exactly.
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 · 91 lines · 100 tokens per session scan A 6c55fea949cb
architecture-review is an agent published in the GitHub repository forcedotcom/sf-skills (974 stars, last pushed today), licensed Apache-2.0. It adds 100 tokens to every session and 1,474 once invoked, about $0.0005 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 2026-09-03.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.