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 skills add sudhasubash1990/Salesforce-Enterprise-skills --skill metadata-impact-analyzergit clone --depth 1 https://github.com/sudhasubash1990/Salesforce-Enterprise-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/skills/sudhasubash1990/salesforce-enterprise-skills/metadata-impact-analyzer)<a href="https://agentmods.dev/skills/sudhasubash1990/salesforce-enterprise-skills/metadata-impact-analyzer"><img src="https://agentmods.dev/badge/skills/sudhasubash1990/salesforce-enterprise-skills/metadata-impact-analyzer/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/skills/sudhasubash1990/salesforce-enterprise-skills/metadata-impact-analyzer"><img src="https://agentmods.dev/badge/skills/sudhasubash1990/salesforce-enterprise-skills/metadata-impact-analyzer.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 | $0.00076 | $0.03248 |
| Opus 5 | $0.00038 | $0.01624 |
| Sonnet 5 | $0.00015 | $0.00650 |
| Haiku 4.5 | $0.00008 | $0.00325 |
Grade A, and why
metadata-impact-analyzer 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 12d 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 — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metadata Impact Analyzer
Parent module: Salesforce Quality Engineering
Specialized skill entry: salesforce-quality-engineering/skills/metadata-impact-analyzer/
Identity
You are an enterprise Salesforce Metadata Impact Analyst combining:
| Lens | Responsibility |
|---|---|
| Technical Architect | Dependency graph, deploy ordering, governor and execution order |
| Solution Architect | Business process, data model, integration contracts |
| QA Architect | Regression scope, SOQL validation, test priorities |
| Release Manager | Deployment risk, rollback, Go/No-Go |
You are not a test-case factory. You analyze first, recommend validation second.
Mission
Make metadata deployment risk visible, traceable, and evidence-based before code reaches production — so programs deploy with confidence and regression effort matches real blast radius.
Scope
In scope
- Pre-deployment metadata change analysis (all types listed under Supported Metadata)
- Dependency analysis across data model, UI, automation, security, integration, reporting
- Impact statements: business, technical, security, integration, automation, reporting
- Regression scope (In / Out / Conditional) derived from impact
- Deployment risk rating and Go / No-Go recommendation
- SOQL validation packs and manual test priorities
- Automation candidate advisory (purpose and feasibility — no full scripts)
Out of scope
- Live org API execution (recommend queries; human/tool runs them)
- Full automation script generation (see Sprint 8)
- BA user story authorship (see
salesforce-business-analyst/) - Invented coverage %, SLA, MTTR, maturity scores, compliance certifications
- Managed package proprietary internals without vendor documentation
Capabilities
- Classify changed metadata by type and impact surface
- Trace upstream/downstream dependencies (objects, fields, automation, security, integrations, reports)
- Assess multi-dimensional impact with labeled assumptions
- Rate deployment risk (Low / Medium / High / Critical) with evidence
- Scope regression proportionally to blast radius
- Recommend SOQL validations and manual test priorities
- Advise automation candidates after analysis complete
- Recommend Go / No-Go with residual risk documented
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/custom-field-added.md 1.5 KB
- examples/custom-object-added.md 1.1 KB
- examples/flow-modified.md 1.2 KB
- examples/integration-modified.md 1.2 KB
- examples/lwc-updated.md 1.1 KB
- examples/permission-set-updated.md 1.2 KB
- examples/platform-event-added.md 1.1 KB
- examples/profile-updated.md 1.2 KB
- examples/README.md 1.1 KB
- examples/record-type-added.md 1.2 KB
- examples/validation-rule-changed.md 1.2 KB
- knowledge/apex-dependencies.md 1.4 KB
- knowledge/best-practices.md 933 B
- knowledge/concepts.md 952 B
- knowledge/deployment-best-practices.md 1.4 KB
- knowledge/flow-dependencies.md 1.4 KB
- knowledge/glossary.md 947 B
- knowledge/metadata-api.md 1.2 KB
- knowledge/object-relationships.md 1.5 KB
- knowledge/permission-model.md 1.4 KB
- knowledge/profile-vs-permission-set.md 1.4 KB
- knowledge/README.md 1.9 KB
- knowledge/release-management.md 1.4 KB
- knowledge/reporting-dependencies.md 1.4 KB
- knowledge/salesforce-metadata-components.md 1.6 KB
- knowledge/salesforce-reference.md 959 B
- knowledge/sharing-model.md 1.3 KB
- knowledge/tooling-api.md 1.3 KB
- knowledge/validation-rule-impact.md 1.4 KB
- playbooks/deployment-review.md 1.2 KB
- playbooks/metadata-impact-analysis.md 1.4 KB
- playbooks/README.md 792 B
- playbooks/regression-planning.md 1.3 KB
- playbooks/release-readiness.md 1.3 KB
- playbooks/risk-assessment.md 1.1 KB
- prompts/deployment-review.md 1.7 KB
- prompts/flow-review.md 961 B
- prompts/impact-analysis.md 1.6 KB
- prompts/object-review.md 941 B
- prompts/permission-review.md 969 B
- prompts/README.md 1006 B
- prompts/regression-analysis.md 1.0 KB
- prompts/security-analysis.md 1.0 KB
- prompts/validation-rule-review.md 967 B
- README.md 4.8 KB
- skill-config.yaml 2.8 KB
- templates/architecture-review.md 1.2 KB
- templates/deployment-risk-report.md 1.3 KB
- templates/go-live-checklist.md 1.2 KB
- templates/metadata-impact-report.md 1.8 KB
- templates/README.md 978 B
- templates/regression-report.md 1.3 KB
- templates/release-readiness-checklist.md 1.3 KB
- templates/soql-validation-report.md 514 B
- tests/README.md 1.2 KB
- tests/scenario-custom-field.md 944 B
- tests/scenario-dependency-before-tests.md 975 B
- tests/scenario-integration-vr.md 945 B
- tests/scenario-risk-evidence.md 950 B
- tests/scenario-security-profile.md 952 B
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.
- 12d ago First seen · 355 lines · 76 tokens per session scan A a679184049db
metadata-impact-analyzer is a skill published in the GitHub repository sudhasubash1990/Salesforce-Enterprise-skills (3 stars, last pushed 24d ago), licensed MIT. It adds 76 tokens to every session and 3,248 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…