Agentforce architecture analyzer
Inventory a Salesforce Agentforce agent's full declared architecture — planner, topics, actions, flows, Apex, prompts — into a readable document and Mermaid graph
- What
- Inventory a Salesforce Agentforce agent's full declared architecture — planner, topics, actions, flows, Apex, prompts — into a readable document and Mermaid graph
- Cost
- Free
- Needs
- a Salesforce org with an Agentforce agent to document (authenticate with `sf org login web --alias <alias>`); the sf CLI (>=2.136.8); Python 3.10+
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @forcedotcom's declared-architecture snapshot for one Agentforce agent: a parallel Tooling SOQL fan-out reads design-time metadata only (`BotDefinition`, `GenAiPlanner*`, `GenAiPlugin*`, `Flow`, `ApexClass`, `GenAiPromptTemplate`) and renders a human-readable architecture document plus a capped Mermaid invocation graph, in about 30–45 seconds, deterministic and fully inline — no subagent. Normalizes both planner shapes (classic ReAct and NGA), surfaces unresolved references instead of dropping them, caches per org/agent with template-aware cache busting, and ships a machine-readable contract for downstream tooling. By @forcedotcom, listed here with credit to its creator. Honest caveats: reads design-time metadata only — no runtime session traces or conversation transcripts; requires the sf CLI authenticated against the target org (`sf org login web`) and Python 3.10+; artifacts cache locally under `~/.vibe`. Apache-2.0 licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Agentforce architecture analyzer is a free skill from @forcedotcom that snapshots the declared architecture of one Agentforce agent. A Tooling SOQL fan-out reads design-time metadata and renders an architecture document plus a capped Mermaid graph, in about 30 to 45 seconds, deterministic, inline, no subagent. It normalizes ReAct and NGA shapes, surfaces unresolved references, and caches per org and agent.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit e5164d9Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a Salesforce org with an Agentforce agent to document (authenticate with `sf org login web --alias <alias>`); the sf CLI (>=2.136.8); Python 3.10+ Install "Agentforce architecture analyzer" for me. It gives the agent @forcedotcom's pipeline to snapshot one Agentforce agent's declared architecture: resolve the bot and planner, fan out 6 parallel Tooling SOQL channels from the planner id, expand discovered flow/apex/prompt references, merge everything into a normalized metadata tree JSON, and render a human-readable architecture document with an embedded Mermaid invocation graph (deterministic, inline, no subagent). Repository: https://raw.githubusercontent.com/forcedotcom/sf-skills/e5164d94d7511c00fa02a5b8b60754b2361e178f/skills/agentforce-architecture-analyze/SKILL.md Pinned version: install the code at commit e5164d94d7511c00fa02a5b8b60754b2361e178f exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "agentforce-architecture-analyze". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. authenticate the sf CLI against my org and pass --org <alias> --agent <api_name> when invoking). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- e5164d9 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.