init

A project setup command that creates or repairs the `.soloflow/` folder used by SoloFlow and asks for a few project preferences.

In plain words
What is it for?
Use it when starting a project or after an update when the `.soloflow/` folder may be incomplete.
Why use it?
It restores missing setup files without replacing files that are already there, helping other SoloFlow commands run correctly.

Command

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/init
Clone the repo
git clone --depth 1 https://github.com/kesteva/soloflow
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,924 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 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 $0.00017 $0.08924
Opus 5 $0.00009 $0.04462
Sonnet 5 $0.00003 $0.01785
Haiku 4.5 $0.00002 $0.00892

Measured 2d ago against content hash 4aeae07bf6ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

init scanned grade D with 3 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- **Question:** "Maestro CLI is required for mobile visual verification but isn't on your PATH. Install it now? (Runs `curl -Ls https://get.maestro.mobile.dev | bash`.)"

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

1. Read `~/.claude/settings.json` via Bash (`cat ~/.claude/settings.json`).

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Question:** "Maestro CLI is required for mobile visual verification but isn't on your PATH. Install it now? (Runs `curl -Ls https://get.maestro.mobile.dev | bash`.)"
commands/init.md · 590 lines

How it starts

The opening of the file, as written. The whole thing — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/soloflow:init

Scaffolds the .soloflow/ state directory that every other SoloFlow command depends on. This command is idempotent — run it once when setting up a project, and re-run it any time you suspect .soloflow/ is missing files (e.g. after a plugin update that adds new state files). Existing files are never overwritten; only missing pieces are created.

After ensuring the directory tree is in place, a short setup wizard asks about visual verification and branching preferences and writes the answers to .soloflow/config.json.


Step 1: Detect state

Run test -d .soloflow via Bash.

  • If .soloflow/ exists → mode is repair. Tell the user:
    Repairing .soloflow/ — checking for missing files...
    
  • Otherwise → mode is fresh. Tell the user:
    Initializing .soloflow/ in this project...
    

Carry the mode forward for the final report. Track two counters throughout Steps 2–3: dirs_created, files_created (everything else is "already present").

Step 2: Ensure directories

For each of these paths, run mkdir -p via Bash. For each path that did NOT exist before the mkdir (check with test -d first, then create), write an empty .gitkeep file into it.

  • .soloflow/active/ideas
  • .soloflow/active/research
  • .soloflow/active/plans
  • .soloflow/active/stuck
  • .soloflow/active/findings
  • .soloflow/active/compound
  • .soloflow/archive/ideas
  • .soloflow/archive/done
  • .soloflow/archive/reviews
  • .soloflow/archive/findings
  • .soloflow/archive/compound
  • .soloflow/active/roadmaps
  • .soloflow/archive/roadmaps

Increment dirs_created for every directory you actually created.

Step 3: Ensure state files

For each of these files, run test -e <path> first. Only write the file if it does not already exist. Never overwrite — the file may contain live user state (sprint data, checkpoint notes). Increment files_created for every file you actually wrote.

(There is no backlog.json. Plan frontmatter status IS the queue — plans live under .soloflow/active/plans/**/TASK-*-plan.md.)

Read the full file on GitHub · 590 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 · 590 lines · 17 tokens per session scan D 4aeae07bf6ca

Subscribe to this mod's changes

init is a command published in the GitHub repository kesteva/soloflow (41 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 8,924 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.