| name | flux-deps |
| description | Show epic dependency graph and execution order. Use when asking 'what's blocking what', 'execution order', 'dependency graph', 'what order should epics run', 'critical path', 'which epics can run in parallel'. |
Flux Dependency Graph
Visualize epic dependencies, blocking chains, and execution phases.
Setup
PLUGIN_ROOT="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}}"
[ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(ls -td ~/.claude/plugins/cache/nairon-flux/flux/*/ 2>/dev/null | head -1)
FLUXCTL="${PLUGIN_ROOT}/scripts/fluxctl"
$FLUXCTL detect --json | jq -e '.exists' >/dev/null && echo "OK: .flux/ exists" || echo "ERROR: run $FLUXCTL init"
command -v jq >/dev/null 2>&1 && echo "OK: jq installed" || echo "ERROR: brew install jq"
Step 1: Gather Epic Data
Build a consolidated view of all epics with their dependencies:
PLUGIN_ROOT="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}}"
[ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(ls -td ~/.claude/plugins/cache/nairon-flux/flux/*/ 2>/dev/null | head -1)
FLUXCTL="${PLUGIN_ROOT}/scripts/fluxctl"
epic_ids=$($FLUXCTL epics --json | jq -r '.epics[].id')
for id in $epic_ids; do
$FLUXCTL show "$id" --json | jq -c '{
id: .id,
title: .title,
status: .status,
plan_review: .plan_review_status,
deps: (.depends_on_epics // [])
}'
done
Step 2: Identify Blocking Chains
Determine which epics are ready vs blocked (pure jq, works on any shell):
PLUGIN_ROOT="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}}"
[ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(ls -td ~/.claude/plugins/cache/nairon-flux/flux/*/ 2>/dev/null | head -1)
FLUXCTL="${PLUGIN_ROOT}/scripts/fluxctl"
epics_json=$($FLUXCTL epics --json | jq -r '.epics[].id' | while read id; do
$FLUXCTL show "$id" --json | jq -c '{id: .id, title: .title, status: .status, deps: (.depends_on_epics // [])}'
done | jq -s '.')
echo "$epics_json" | jq -r '
# Build status lookup
(map({(.id): .status}) | add // {}) as $status |
# Check each non-done epic
.[] | select(.status != "done") |
.id as $id | .title as $title |
# Find deps that are not done
([.deps[] | select($status[.] != "done")] | join(", ")) as $blocked_by |
if ($blocked_by | length) == 0 then
"READY: \($id) - \($title)"
else
"BLOCKED: \($id) - \($title) (by: \($blocked_by))"
end
'
Step 3: Compute Execution Phases
Group epics into parallel execution phases:
PLUGIN_ROOT="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}}"
[ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(ls -td ~/.claude/plugins/cache/nairon-flux/flux/*/ 2>/dev/null | head -1)
FLUXCTL="${PLUGIN_ROOT}/scripts/fluxctl"
epics_json=$($FLUXCTL epics --json | jq -r '.epics[].id' | while read id; do
$FLUXCTL show "$id" --json | jq -c '{id: .id, title: .title, status: .status, deps: (.depends_on_epics // [])}'
done | jq -s '.')
echo "$epics_json" | jq '
# Build status lookup
(map({(.id): .status}) | add // {}) as $status |
# Filter to non-done epics
[.[] | select(.status != "done")] as $open |
# Assign phases iteratively
reduce range(10) as $phase (
{assigned: [], result: [], open: $open};
.assigned as $assigned |
.open as $remaining |
# Find epics not yet assigned whose deps are all done or in earlier phases
([.open[] | select(
([.id] | inside($assigned) | not) and
((.deps // []) | all(. as $d | $status[$d] == "done" or ($assigned | index($d))))
)] | map(.id)) as $ready |
if ($ready | length) > 0 then
.result += [{phase: ($phase + 1), epics: [.open[] | select(.id | IN($ready[]))]}] |
.assigned += $ready
else . end
) |
.result
'
Output Format
Present results as:
## Epic Dependency Graph
### Status Overview
| Epic | Title | Status | Dependencies | Blocked By |
|------|-------|--------|--------------|------------|
| **fn-1-add-auth** | Add Authentication | **READY** | - | - |
| fn-2-add-oauth | Add OAuth Login | blocked | fn-1-add-auth | fn-1-add-auth |
| fn-3-user-profile | User Profile Page | blocked | fn-1-add-auth, fn-2-add-oauth | fn-2-add-oauth |
### Execution Phases
| Phase | Epics | Can Start |
|-------|-------|-----------|
| **1** | fn-1-add-auth | **NOW** |
| 2 | fn-2-add-oauth | After Phase 1 |
| 3 | fn-3-user-profile | After Phase 2 |
### Critical Path
fn-1-add-auth → fn-2-add-oauth → fn-3-user-profile (3 phases)
Quick One-Liner
For a fast dependency check:
PLUGIN_ROOT="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}}"
[ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(ls -td ~/.claude/plugins/cache/nairon-flux/flux/*/ 2>/dev/null | head -1)
FLUXCTL="${PLUGIN_ROOT}/scripts/fluxctl"
$FLUXCTL epics --json | jq -r '.epics[] | select(.status != "done") | "\(.id): \(.title) [\(.status)]"'
When to Use
- "What's the execution order for epics?"
- "What's blocking progress?"
- "Show me the dependency graph"
- "What's the critical path?"
- "Which epics can run in parallel?"
- "Why is Ralph working on X?"
- "What should I work on next?"
Gotchas
- The graph only reflects dependencies persisted in
.flux/. If someone changed work informally without recording deps, the graph will be incomplete.
- Use
fluxctl output as the source of truth. Do not infer dependency edges from titles, branch names, or conversation context.
- Closed work can hide the current bottleneck. Favor non-done epics when explaining what is blocking forward progress.
Update Check (End of Command)
ALWAYS run at the very end of command execution:
PLUGIN_ROOT="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}}"
[ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(ls -td ~/.claude/plugins/cache/nairon-flux/flux/*/ 2>/dev/null | head -1)
UPDATE_JSON=$("$PLUGIN_ROOT/scripts/version-check.sh" 2>/dev/null || echo '{"update_available":false}')
UPDATE_AVAILABLE=$(echo "$UPDATE_JSON" | jq -r '.update_available')
LOCAL_VER=$(echo "$UPDATE_JSON" | jq -r '.local_version')
REMOTE_VER=$(echo "$UPDATE_JSON" | jq -r '.remote_version')
If update available, append to output:
---
Flux update available: v${LOCAL_VER} → v${REMOTE_VER}
Update Flux from the same source you installed it from, then restart your agent session.
---