A command for starting a vertical flywheel, meaning a focused workflow around one area of work, from a natural-language request. It follows TDD, or test-driven development, by checking what is missing, adding a minimum working setup, and then adding safeguards.

It is for bootstrapping an Emerge workflow, optionally preparing a remote runner, and reporting whether initialization succeeded.

It gives the setup process an ordered way to identify gaps, create the initial system, and verify it.

init — Command for coding agents by jianzhichun: A command for starting a vertical flywheel, meaning a…

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/jianzhichun/emerge/init

Clone the repo

git clone --depth 1 https://github.com/jianzhichun/emerge

Or install emerge, the plugin that ships this one along with the rest of its 15 skills, 10 commands, 3 agents, 24 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/jianzhichun/emerge/init.svg)](https://agentmods.dev/commands/jianzhichun/emerge/init)

Your own site

<a href="https://agentmods.dev/commands/jianzhichun/emerge/init"><img src="https://agentmods.dev/badge/commands/jianzhichun/emerge/init.svg" alt="Measured on agentmods" height="20"></a>

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 517 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 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	$0.00009	$0.00517
Opus 5	$0.00005	$0.00259
Sonnet 5	$0.00002	$0.00103
Haiku 4.5	$0.00001	$0.00052

Measured 5d ago against content hash b705d98b3261, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

init scanned grade C with 2 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 5d 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.

- send the printed `curl ... | bash` or `irm ... | iex` to the operator; they run it on the target machine (installs deps, writes `~/.emerge/runner-config.json`, starts runner)

Makes network callslowCapability

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

- send the printed `curl ... | bash` or `irm ... | iex` to the operator; they run it on the target machine (installs deps, writes `~/.emerge/runner-config.json`, starts runner)

commands/init.md · 37 lines

What it actually says

Interpret the user's /emerge:init ... message as natural-language bootstrap intent.

Execution rules:

Use the initializing-vertical-flywheel skill as the primary workflow.
Treat user text as the source of context; do not require parameter-style declarations.
Follow TDD evidence order:

RED baseline (what is missing now)
GREEN minimum bootstrap
REFACTOR guardrails

If remote execution is required, set up the runner first (operator self-install — no SSH from CC):

generate install commands from local plugin root:
- python3 "${CLAUDE_PLUGIN_ROOT}/scripts/repl_admin.py" runner-install-url --target-profile "<target_profile>" --pretty
send the printed curl ... | bash or irm ... | iex to the operator; they run it on the target machine (installs deps, writes ~/.emerge/runner-config.json, starts runner)
optionally use Cockpit → Monitors tab → Add Runner to copy the same URLs
run python3 "${CLAUDE_PLUGIN_ROOT}/scripts/repl_admin.py" runner-status --pretty
if unreachable, do not continue pipeline initialization blindly

If required context is missing, ask only minimal clarifying questions.
Report:

status: init_ok / degraded / blocked
created/updated assets
verification evidence
next recommended action

Connector notes handling (must match current architecture):

keep ~/.emerge/connectors/<connector>/NOTES.md concise and operational (no long dumps)
when reverse flywheel synthesis is desired, also create ~/.emerge/connectors/<connector>/synthesis_hints.yaml with scripting imports, event-to-API examples, verify guidance, and timeout notes
SessionStart only exposes a compact connector index
full NOTES are injected on-demand by PreToolUse on the first approved icc_exec / icc_span_open / icc_crystallize call per connector

Status rules:

init_ok: runner reachable (if needed), assets created, icc_exec smoke checks pass.
degraded: partial success (assets created but verification failed or policy degraded).
blocked: missing prerequisites (runner unreachable, missing host context, or required toolchain absent).

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.

5d ago First seen · 37 lines · 9 tokens per session scan C b705d98b3261

Subscribe to this mod's changes

init is a command published in the GitHub repository jianzhichun/emerge (107 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 517 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Planning TDD Testing

init

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade C, and why

Downloads and executes remote codehighSupply chain

Makes network callslowCapability

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

tdd-requirements

pm-auto-design2dev

dashboard

usage-add

hub-tdd

eval