forcedotcom/sf-skills is a collection of reusable instructions that help AI coding agents build and work with Salesforce applications and platform features. Developers use it for Agentforce agents, Lightning apps, Flow, Apex, SOQL, Lightning Web Components, and related Salesforce configuration. The catalogue entries are the repository’s skills, plugins, commands, MCP servers, and agents for AI tools that support skills.
Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add forcedotcom/sf-skills/plugin install agentforce-adlcWrote 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/forcedotcom/sf-skills/agentforce-architecture-analyze)<a href="https://agentmods.dev/skills/forcedotcom/sf-skills/agentforce-architecture-analyze"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/agentforce-architecture-analyze/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/forcedotcom/sf-skills/agentforce-architecture-analyze"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/agentforce-architecture-analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 27 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
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 | $0.00145 | $0.04700 |
| Opus 5.5 | $0.00058 | $0.01880 |
| Sonnet 5.5 | $0.00029 | $0.00940 |
| Haiku 4.5 | $0.00015 | $0.00470 |
Grade A, and why
agentforce-architecture-analyze 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 9d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentforce-architecture-analyze — declared architecture snapshot
Design-time metadata tree for one Agentforce agent: planner → topics → actions → flows → Apex → prompts → NGA plugins. Reads declared metadata only — BotDefinition, GenAiPlanner*, GenAiPlugin*, GenAiFunction*, Flow, ApexClass, GenAiPromptTemplate. Does not read runtime audit rows.
Runtime budget: 30–45s typical, ≤60s hard cap on reference fixtures. Sequential baseline would be 90–220s; parallel Tooling SOQL fan-out delivers a 3–5× speedup. Large bots with many flows scale approximately linearly — each flow metadata retrieve is one round-trip.
Runs inline — no subagent. Every phase is deterministic file processing.
If the user hasn't named an agent
Trigger condition: $ARGUMENTS names no agent (no --agent flag and no exact BotDefinition API name in the prose). Never invent an agent name. Instead, discover what the org actually contains — one read-only query, no pipeline yet. Use the --org alias if given, otherwise the default target org (omit --target-org):
sf data query --query "SELECT DeveloperName, MasterLabel FROM BotDefinition ORDER BY DeveloperName" \
[--target-org <alias>] --json
If the user gave no org alias, the pipeline block defaults --org to the CLI default target org itself (sf config get target-org --json → .result[0].value) — you don't need to resolve it.
Then branch on the rows returned:
- Zero agents — tell the user the org has no Agentforce agents and stop. Do not fabricate an agent or a tree.
- Exactly one agent, or exactly one whose
DeveloperName/MasterLabelmatches the user's description (e.g. "support", "service", "sales") — use it, say explicitly which agent you picked and why, then run the pipeline block below withARG_AGENT=<DeveloperName>(andARG_ORG=<alias>if the user named one) set as its first lines, e.g.ARG_AGENT=Customer_Support_Agent. The block readsARG_*from the environment; flags in$ARGUMENTSstill override. - Otherwise — print the block below, with the discovered agents listed as a numbered
DeveloperName — MasterLabeltable under the first line, and wait for the user to pick. - Query fails (no default org, auth error) — print the block below without the list.
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.
- assets/cli/describe_sobject.yaml 317 B
- assets/cli/describe_tooling_sobject.yaml 347 B
- assets/cli/list_metadata_genaiprompttemplate.yaml 342 B
- assets/cli/org_display.yaml 280 B
- assets/cli/retrieve_genai_plugin.yaml 391 B
- assets/cli/show_access_token.yaml 700 B
- assets/mermaid/action_tree.mmd 986 B
- assets/mermaid/data_flow.mmd 893 B
- assets/mermaid/dependency_graph.mmd 810 B
- assets/mermaid/invocation_sequence.mmd 1004 B
- assets/mermaid/planner_state.mmd 813 B
- assets/soql/apex_class_bodies_by_ids.soql 103 B
- assets/soql/apex_class_bodies_by_names.soql 102 B
- assets/soql/bot_definition_details.soql 152 B
- assets/soql/bot_version_lookup.soql 186 B
- assets/soql/flow_definition_by_ids.soql 115 B
- assets/soql/flow_definition_ids_by_names.soql 146 B
- assets/soql/flow_definition_view_by_durable_ids.soql 180 B
- assets/soql/flow_metadata_by_id.soql 73 B
- assets/soql/functions_by_plugins.soql 317 B
- assets/soql/planner_attrs_by_parent_ids.soql 156 B
- assets/soql/planner_bundle_functions.soql 93 B
- assets/soql/planner_definition_by_agent_chain.soql 174 B
- assets/soql/plugin_functions_by_plugin_ids.soql 93 B
- assets/soql/plugin_instructions_by_plugin_ids.soql 168 B
- assets/soql/plugins_by_planner.soql 199 B
- README.md 8.5 KB
- references/architecture_sections.md 8.3 KB
- references/contract.json 12 KB
- references/soql_fields.md 25 KB
- scripts/_shared/__init__.py 82 B runs code
- scripts/_shared/fs_guard.py 13 KB runs code
- scripts/_shared/paths.py 3.9 KB runs code
- scripts/_shared/runtime.py 2.0 KB runs code
- scripts/_shared/sql.py 355 B runs code
- scripts/cache_check.py 8.9 KB runs code
- scripts/config.py 5.9 KB runs code
- scripts/emit_env.py 5.1 KB runs code
- scripts/emit_result.py 11 KB runs code
- scripts/fetch_soql.py 26 KB runs code
- scripts/finalize.py 12 KB runs code
- scripts/main.py 114 KB runs code
- scripts/metadata_listing.py 9.5 KB runs code
- scripts/parallel_retrieve.py 3.3 KB runs code
- scripts/parse_bundle.py 7.9 KB runs code
- scripts/parse_wave.py 36 KB runs code
- scripts/probe_channels.py 11 KB runs code
- scripts/render_architecture.py 40 KB runs code
- scripts/resolve_bot.py 9.4 KB runs code
- scripts/resolve_invocation_target.py 4.8 KB runs code
- scripts/rest_client.py 34 KB runs code
- scripts/retrieve_planner.py 464 B runs code
- scripts/sanitize.py 1013 B runs code
- scripts/sf_cli.py 12 KB runs code
- scripts/soql_loader.py 11 KB runs code
- scripts/summarize_tree.py 4.6 KB runs code
- scripts/tests/__init__.py 0 B runs code
- scripts/tests/_bootstrap.py 843 B runs code
- scripts/tests/fixtures/__init__.py 0 B runs code
- scripts/tests/fixtures/genai_payloads.py 13 KB runs code
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.
- 9d ago Changed · +49 lines 1a28c6a9abcc
- 1mo ago First seen · 240 lines · 145 tokens per session scan A 7f5279acd1bb
agentforce-architecture-analyze is a skill published in the GitHub repository forcedotcom/sf-skills (1,097 stars, last pushed today), licensed Apache-2.0. It adds 145 tokens to every session and 4,700 once invoked, about $0.0006 per session on Opus 5.5. 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 skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…