A command for turning a rough idea or a collection of ideas into a clear implementation plan with tasks. It can first extract ideas from raw notes and then break them into work that is ready to execute.

Use it to clarify one idea, sort a brain dump into separate ideas, research when configured, and refine the results into detailed tasks.

It removes the uncertainty between having an idea and knowing exactly what needs to be built next.

planner — Command by kesteva

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/kesteva/soloflow/planner

Clone the repo

git clone --depth 1 https://github.com/kesteva/soloflow

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 13,144 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.

Model	Per session	Once invoked
Fable 5	$0.00020	$0.13144
Opus 5	$0.00010	$0.06572
Sonnet 5	$0.00004	$0.02629
Haiku 4.5	$0.00002	$0.01314

Measured 2d ago against content hash 84c2b3863568, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planner 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.

commands/planner.md · 838 lines

How it starts

The opening of the file, as written. The whole thing — 838 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/soloflow:planner

Unified entry for the SoloFlow planning phase. Two internal phases:

Phase 1 — Extract (optional) produces IDEA file(s) from raw input. Two sub-modes: single-idea (clarify + idea-extractor agent + research) or multi-idea (heuristic braindump classification).
Phase 2 — Refine turns IDEA file(s) into execution-ready plans via the task-decomposer + parallel detailers.

/soloflow:idea-extractor and /soloflow:braindump are preconfigured wrappers that dispatch into this command with --mode=single-idea or --mode=multi-idea prepended.

The user's input is: $ARGUMENTS

Model + limits resolution

Resolve the relevant config values once. Run via Bash:

node "${CLAUDE_PLUGIN_ROOT}/scripts/config/resolve.js" \
    --key models.task_refiner --key models.task_decomposer \
    --key models.idea_extractor --key models.researcher \
    --key limits.context_limit_respawn_max \
    --key parallelism.task_refiner_parallel \
    --key phases.clarify --key phases.research \
    --key parallelism.phase_worktrees \
    --fallback opus --fallback sonnet --fallback sonnet --fallback sonnet \
    --fallback 3 --fallback true --fallback true --fallback true \
    --fallback false

Lines: 1=task_refiner model · 2=task_decomposer model · 3=idea_extractor model · 4=researcher model · 5=respawn cap · 6=task-refiner parallelism toggle · 7=clarify-phase toggle · 8=research-phase toggle · 9=phase-worktrees toggle.

Step 0: Initialize

If .soloflow/ does not exist, report "SoloFlow not initialized. Run /soloflow:init first." and stop.

Step 0.5: Mode resolution

Inspect $ARGUMENTS and route into one of three modes (single-idea, multi-idea, refine). Carry mode forward into the appropriate phase.

refine (existing IDEA) — If $ARGUMENTS matches ^IDEA-\d{3,}$ (case-insensitive), set mode = refine, target_id = <argument>. Skip Phase 1, jump straight to Phase 2.
single-idea — Else if $ARGUMENTS matches ^--mode=single-idea(\s+|$) (with optional whitespace + remaining text), set mode = single-idea, raw = <$ARGUMENTS with the leading token and following whitespace stripped>. If raw is empty, fall back to a follow-up AskUserQuestion (free-form: "Describe the idea") and set raw to the response. Run Phase 1a. After Phase 1a completes, fall through to Phase 2 unless the user opted to defer refinement.

Read the full file on GitHub · 838 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.

2d ago First seen · 838 lines · 20 tokens per session scan A 84c2b3863568

Subscribe to this mod's changes

planner is a command published in the GitHub repository kesteva/soloflow (40 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 13,144 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.

Planning

planner

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/soloflow:planner

Model + limits resolution

Step 0: Initialize

Step 0.5: Mode resolution

What this file has done since we first saw it

Other commands, from other repositories

git

checklist

clarify

specify

analyze

constitution