agentforce-architecture-analyze

What the source does

• FilesystemDeclared5 observations
• NetworkDeclared5 observations
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

render_architecture.load_mermaid("../../../etc/passwd")

self.soql_loader.load_soql("../../../etc/passwd")

self.soql_loader.load_soql("../../../evil")

"../../../evil", list_params={"IDS": ["A"]},

Audit 0.4.1 · source sha 817611589af1 · 21 Oct 2026Report an issue or request a re-scan

• Publisherforcedotcom GitHub organizationOwner of the repository this skill is read from
• Source folderforcedotcom/sf-skills/skills/agentforce-architecture-analyzeThe exact folder we audited
• LicenceApache-2.0As the repository states it
• Commit pinned for this verdict817611589af1A new audit runs when the source changes
• Repository statusNot archivedLast push 1 day ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Declared architecture snapshot for one Agentforce agent: planner, topics, actions, flows, Apex, prompt templates, and NGA plugins. Renders a human-readable architecture document and Mermaid invocation graph from…

---
name: agentforce-architecture-analyze
description: "Declared architecture snapshot for one Agentforce agent: planner, topics, actions, flows, Apex, prompt templates, and NGA plugins. Renders a human-readable architecture document and Mermaid invocation graph from design-time metadata (not runtime audit rows). TRIGGER when user asks to describe, diagram, inventory, audit, document, or diff (e.g. v3 vs v5) the architecture / action tree / topic structure / tool inventory of a specific agent by agent API name in a specific org. DO NOT TRIGGER for runtime session traces, conversation transcripts, generation timings, or gateway audit chains — this skill reads design-time metadata only (use agentforce-d360-analyze for session traces)."
metadata:
  version: "1.0"
  domains: ["Agentforce"]
  minApiVersion: "64.0"
  relatedSkills:
    - "agentforce-d360-analyze"
  cliTools:
    - tool: ["sf"]
      semver: ">=2.136.8"
    - tool: ["python3"]
      semver: ">=3.10.0"
---

# 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`):

```bash
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`/`MasterLabel` matches 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 with `ARG_AGENT=<DeveloperName>` (and `ARG_ORG=<alias>` if the user named one) set as its first lines, e.g. `ARG_AGENT=Customer_Support_Agent`. The block reads `ARG_*` from the environment; flags in `$ARGUMENTS` still override.
- **Otherwise** — print the block below, with the discovered agents listed as a numbered `DeveloperName — MasterLabel` table 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.

> Which agent should I document, and in which org?
>
> I need:
> - **Agent API name** — the `DeveloperName` of the `BotDefinition` (e.g. `MyAgent`, `MySalesAgent`). Not the label.
> - **Org alias** — for `sf` CLI auth (the alias you configured with `sf org login`)
>
> Optional:
> - **Version** — an `agent_version_api_name` like `v5`. If omitted, I'll resolve the active `BotVersion`.
> - **`--force`** — ignore cached tree; re-fetch everything.
> - **`--reprobe`** — re-run the 7-day channel-probe cache (only needed after a Salesforce release).
>
> I'll run the metadata pipeline inline. Artifacts land under `~/.vibe/data/agentforce-architecture-analyze/<org_id15>/<agent_api_name>__<agent_version>/` (overridable with `--data-dir`).

## Pipeline invocation

Run this block once the agent is known — from `--agent <api_name>` in `$ARGUMENTS`, or preset as `ARG_AGENT=<DeveloperName>` after discovery. `--org` (or `ARG_ORG`) is optional; without it the CLI default target org is used. One `python3` invocation drives the full pipeline. `main.py` writes `.emit_ctx.json`; `emit_result.py` reads it and prints the final `=== RESULT ===` block last to stdout.

```bash
set -euo pipefail

# zsh arrays are 1-indexed by default; bash arrays are 0-indexed.
# This block uses 0-indexed semantics throughout (_args[$i] starting at i=0),
# so under zsh + `set -u` the very first read of `_args[0]` would trip
# `parameter not set`. KSH_ARRAYS makes zsh treat arrays as 0-indexed,
# matching the bash shebang's expectation. No-op under bash.
[ -n "${ZSH_VERSION:-}" ] && setopt KSH_ARRAYS

# <SKILL_DIR> = absolute path of this skill's own directory (the folder holding
# this SKILL.md); substitute it from the skill path in context. Runtimes install
# skills in different places, so also probe the known install roots and use the
# first that actually contains this skill's scripts. An exported SKILL_ROOT wins.
_skill=agentforce-architecture-analyze
for _c in "${SKILL_ROOT:-}" "<SKILL_DIR>" \
          "${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT/skills/$_skill}" \
          "${VIBES_SKILLS_DIR:+$VIBES_SKILLS_DIR/$_skill}" \
          "$HOME/.claude/skills/$_skill" "$PWD/.claude/skills/$_skill" \
          "${PLUGIN_ROOT:-$HOME/.vibe/skills}/$_skill"; do
  [ -n "$_c" ] || continue
  # Some stagers (ADK eval) nest the bundled files under <skill>/artifacts/.
  for _r in "$_c" "$_c/artifacts"; do
    [ -f "$_r/scripts/main.py" ] && { SKILL_ROOT="$_r"; break 2; }
  done
done
[ -f "${SKILL_ROOT:-}/scripts/main.py" ] || { echo "$_skill: scripts not found — set SKILL_ROOT to this skill's directory" >&2; exit 1; }

# Argument parser. Accepts both `--org foo` and `--org=foo`.
# `$ARGUMENTS` is the raw user input Clau

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

1. 2026-10-21
   ✓SAFE B 89 / 100

   first audit · source 817611589af1

Questions about agentforce-architecture-analyze

• github.com/forcedotcom/sf-skills/tree/main/skills/agentforce-arc — the audited source at commit 817611589af1 and every finding aboveObserved · 21 Oct 2026

Spotted something wrong? Report a correction · Methodology