plan

An implementation-planning command that turns a project specification into a detailed plan for building a feature or larger piece of work.

In plain words
What is it for?
Use it to plan features or epics, choosing a deeper or quicker planning mode when needed.
Why use it?
It helps organize research, decisions, and work stages before coding begins.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/marcusgoll/spec-flow/plan
Clone the repo
git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,118 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.06118
Opus 5 $0.00009 $0.03059
Sonnet 5 $0.00004 $0.01224
Haiku 4.5 $0.00002 $0.00612

Measured 2d ago against content hash 6a39de052757, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan 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 2d 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.

.claude/commands/phases/plan.md · 765 lines

How it starts

The opening of the file, as written. The whole thing — 765 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/plan — Implementation Plan Generator (Thin Wrapper)

v11.0 Architecture: This command spawns the isolated plan-phase-agent via Task(). All planning logic runs in isolated context with question batching.

Active Feature: !ls -td specs/[0-9]*-* 2>/dev/null | head -1 || echo "none"

Active Epic: !ls -td epics/[0-9]*-* 2>/dev/null | head -1 || echo "none"

Interaction State: !cat specs/*/interaction-state.yaml 2>/dev/null | head -10 || echo "none"

Planning Depth Preference: !bash .spec-flow/scripts/utils/load-preferences.sh --key "planning.auto_deep_mode" --default "false" 2>/dev/null || echo "false"

Is Epic Context: ![ -d "$(ls -td epics/[0-9]*-* 2>/dev/null | head -1)" ] && echo "true" || echo "false"

<planning_depth>

Planning Depth Mode (--deep / --quick)

Detect flags from arguments:

  • --deep → Force ultrathink/craftsman mode
  • --quick → Force standard mode (skip ultrathink)
  • Neither → Check preference hierarchy

Preference hierarchy (when no flags):

  1. planning.auto_deep_mode: true → ultrathink by default
  2. Epic context → ultrathink (via deep_planning_triggers.epic_features)
  3. Complexity threshold exceeded → ultrathink
  4. Default → standard planning

When ultrathink is active:

  1. Load skill: Skill("ultrathink")
  2. Add assumption-questioning step after research
  3. Add simplification review before finalizing
  4. Generate craftsman-decision.md artifact alongside plan.md

Determine mode:

# Check if --deep or --quick flag present in arguments
ARGS="$ARGUMENTS"
DEEP_FLAG=$(echo "$ARGS" | grep -q "\-\-deep" && echo "true" || echo "false")
QUICK_FLAG=$(echo "$ARGS" | grep -q "\-\-quick" && echo "true" || echo "false")

# Load preference
AUTO_DEEP=$(bash .spec-flow/scripts/utils/load-preferences.sh --key "planning.auto_deep_mode" --default "false")

# Detect epic context
IS_EPIC=$([ -d "$(ls -td epics/[0-9]*-* 2>/dev/null | head -1)" ] && echo "true" || echo "false")

# Determine final mode
if [ "$DEEP_FLAG" = "true" ]; then
    PLANNING_MODE="deep"
elif [ "$QUICK_FLAG" = "true" ]; then
    PLANNING_MODE="standard"
elif [ "$AUTO_DEEP" = "true" ]; then
    PLANNING_MODE="deep"
elif [ "$IS_EPIC" = "true" ]; then
    PLANNING_MODE="deep"
else
    PLANNING_MODE="standard"
fi

echo "Planning mode: $PLANNING_MODE"

</planning_depth>

Read the full file on GitHub · 765 lines

Changes

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.

  1. 2d ago First seen · 765 lines · 18 tokens per session scan A 6a39de052757

Subscribe to this mod's changes

plan is a command published in the GitHub repository marcusgoll/Spec-Flow (91 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 6,118 once invoked, about $0.0001 per session on Opus 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 2026-08-30.