Agentforce Architecture Analyze

sf data query --query "SELECT DeveloperName, MasterLabel FROM BotDefinition ORDER BY DeveloperName" \
  [--target-org <alias>] --json

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 Claude Code substitutes; it may be unset
# or plain prose. Each ARG_* starts from the environment, so a value resolved
# during discovery can be preset (e.g. `ARG_AGENT=MyAgent` on the first line);
# flags in $ARGUMENTS still override.
ARG_ORG="${ARG_ORG:-}"
ARG_AGENT="${ARG_AGENT:-}"
ARG_VERSION="${ARG_VERSION:-}"
ARG_FORCE="${ARG_FORCE:-}"
ARG_REPROBE="${ARG_REPROBE:-}"
ARG_PARALLELISM="${ARG_PARALLELISM:-}"
ARG_MAX_MERMAID="${ARG_MAX_MERMAID:-}"

# Word-split $ARGUMENTS (zsh needs SH_WORD_SPLIT for that) with globbing off
# so prose like `*` never expands to filenames.
[ -n "${ZSH_VERSION:-}" ] && setopt SH_WORD_SPLIT
set -f
# shellcheck disable=SC2206
_args=(${ARGUMENTS:-})
set +f
i=0
while [ $i -lt ${#_args[@]} ]; do
 tok="${_args[$i]}"
 case "$tok" in
 --org=*) ARG_ORG="${tok#--org=}" ;;
 --org) i=$((i+1)); ARG_ORG="${_args[$i]:-}" ;;
 --agent=*) ARG_AGENT="${tok#--agent=}" ;;
 --agent) i=$((i+1)); ARG_AGENT="${_args[$i]:-}" ;;
 --version=*) ARG_VERSION="${tok#--version=}" ;;
 --version) i=$((i+1)); ARG_VERSION="${_args[$i]:-}" ;;
 --parallelism=*) ARG_PARALLELISM="${tok#--parallelism=}" ;;
 --parallelism) i=$((i+1)); ARG_PARALLELISM="${_args[$i]:-}" ;;
 --max-mermaid-nodes=*) ARG_MAX_MERMAID="${tok#--max-mermaid-nodes=}" ;;
 --max-mermaid-nodes) i=$((i+1)); ARG_MAX_MERMAID="${_args[$i]:-}" ;;
 --force) ARG_FORCE="1" ;;
 --reprobe) ARG_REPROBE="1" ;;
 esac
 i=$((i+1))
done

# No org named anywhere: fall back to the sf CLI default target org
# (`sf config get target-org --json` -> .result[0].value). Extracted with sed
# so the block needs neither jq nor an inline interpreter; any failure leaves
# ARG_ORG empty and the usage block below fires.
if [ -z "$ARG_ORG" ] && command -v sf >/dev/null 2>&1; then
 _cfg="$(sf config get target-org --json 2>/dev/null || true)"
 _cfg="$(printf '%s\n' "$_cfg" | sed -n 's/.*"value"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p' || true)"
 ARG_ORG="${_cfg%%$'\n'*}"
fi

# Usage block if required flags missing. Agent reads stderr,
# prints verbatim, and stops — does NOT pre-run main.py.
if [ -z "$ARG_ORG" ] || [ -z "$ARG_AGENT" ]; then
 cat >&2 <<'USAGE'
> Which agent should I document, and in which org?
>
> I need:
> - **Agent API name** — the BotDefinition.DeveloperName (e.g. `MyAgent`)
> - **Org alias** — for `sf` CLI auth (the alias you configured with `sf org login`);
>   only needed when no default target org is set (`sf config set target-org <alias>`)
>
> Optional flags:
> - `--version v5` — pin a specific BotVersion (default: Active+highest)
> - `--force` — bypass cache
> - `--reprobe` — force channel-probe refresh
> - `--parallelism N` — ThreadPoolExecutor size (default 5)
> - `--max-mermaid-nodes N` — cap Mermaid node count (default 80)
USAGE
 exit 2
fi

# Fresh work dir per invocation. Epoch + random suffix avoids collisions
# between concurrent runs on the same host.
WORK_DIR="/tmp/agentforce-architecture-analyze-$(date +%s)-$RANDOM"
mkdir -p "$WORK_DIR"

# Input validation at the boundary, BEFORE any python3 call.
# fs_guard exits 1 and prints an INVALID_INPUT RESULT block on failure;
# `|| exit 1` is mandatory — bare calls silently continue past failures.
python3 "$SKILL_ROOT/scripts/_shared/fs_guard.py" "$ARG_AGENT" agent_api_name api_name || exit 1
python3 "$SKILL_ROOT/scripts/_shared/fs_guard.py" "$ARG_ORG" org_alias not_empty || exit 1
python3 "$SKILL_ROOT/scripts/_shared/fs_guard.py" "$WORK_DIR" WORK_DIR symlink || exit 1
python3 "$SKILL_ROOT/scripts/_shared/fs_guard.py" "$WORK_DIR" WORK_DIR owned || exit 1
if [ -n "$ARG_VERSION" ]; then
 python3 "$SKILL_ROOT/scripts/_shared/fs_guard.py" "$ARG_VERSION" agent_version api_name || exit 1
fi

# Single python3 call drives all pipeline phases. main.py writes
# `.emit_ctx.json` into $WORK_DIR — emit_result.py then renders the
# RESULT block from that ctx. No subprocess-per-phase.
_main_args=(--org-alias "$ARG_ORG" --agent "$ARG_AGENT" --work-dir "$WORK_DIR")
[ -n "$ARG_VERSION" ] && _main_args+=(--version "$ARG_VERSION")
[ -n "$ARG_FORCE" ] && _main_args+=(--force)
[ -n "$ARG_REPROBE" ] && _main_args+=(--reprobe)
[ -n "$ARG_PARALLELISM" ] && _main_args+=(--parallelism "$ARG_PARALLELISM")
[ -n "$ARG_MAX_MERMAID" ] && _main_args+=(--max-mermaid-nodes "$ARG_MAX_MERMAID")

# main.py returns nonzero on terminal failures; we DON'T short-circuit —
# emit_result still publishes the failure RESULT block. `set -e` is
# temporarily relaxed around this single call.
set +e
python3 "$SKILL_ROOT/scripts/main.py" "${_main_args[@]}"
_rc=$?
set -e

# Final RESULT block is emit_result.py's stdout — MUST be the last thing
# stdout sees. emit_result exits 0 on render success; the bash harness
# propagates main.py's rc for the agent's exit status.
WORK_DIR="$WORK_DIR" python3 "$SKILL_ROOT/scripts/emit_result.py"
exit "$_rc"

<agent>_<ver>_metadata_tree.json   primary artifact — normalized planner/topic/action/flow/apex/prompt/plugin tree
<agent>_<ver>_architecture.md      human-readable section-by-section rendering (H1 + 7 numbered sections, plus a conditional Dependency graph appendix). Mermaid diagrams are embedded inside the relevant sections (Action tree, Data flow, and Dependency graph)

resolve_bot.py        → BotDefinition + BotVersion + planner name lookup
retrieve_planner.py   → Metadata API zip retrieve for GenAiPlannerBundle (+ NGA plugins if present)
parallel_retrieve.py  → 6 parallel Tooling SOQL channels fan out from the planner id
                          (resolved by the `planner_definition_by_agent_chain` seed query):
                          - plugins_by_planner (GenAiPluginDefinition)
                          - planner_bundle_functions (GenAiPlannerFunctionDef join)
                          - functions_by_plugins (GenAiFunctionDefinition)
                          - planner_attrs_by_parent_ids (GenAiPlannerAttrDefinition)
                          - plugin_functions_by_plugin_ids (GenAiPluginFunctionDef join)
                          - plugin_instructions_by_plugin_ids (GenAiPluginInstructionDef)
parse_bundle.py       → parse retrieved XML into normalized node shapes
parse_wave.py         → BFS expansion: flow/apex/prompt refs discovered in nodes
                          → SOQL for Flow/Apex bodies (batched by id list)
                          → Metadata retrieve ONLY for GenAiPromptTemplate (+ NGA external plugins conditionally)
finalize.py           → merge waves into metadata_tree.json
render_architecture.py → <agent>_<ver>_architecture.md + Mermaid invocation graph (capped at --max-mermaid-nodes)