A default entry command that determines which workflow should handle the operator's request. It first checks whether the repository has been initialized and then reads the stored project state.

Use it when you do not know which command to run next, when bootstrapping a repository, or when continuing an unfinished workflow.

It gives an unstructured starting prompt a clear next step and avoids treating file existence or conversation history as proof of project progress.

start — Command by nicelight

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/nicelight/devrails-26/start

Clone the repo

git clone --depth 1 https://github.com/nicelight/DevRails-26

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 582 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	$0.00032	$0.00582
Opus 5	$0.00016	$0.00291
Sonnet 5	$0.00006	$0.00116
Haiku 4.5	$0.00003	$0.00058

Measured 2d ago against content hash 48dbce500526, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start 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.

skills/_shared/references/commands/start.md · 66 lines

What it actually says

/start — Resolve next workflow owner

<input_contract> Use $ARGUMENTS as operator focus when present.

If .memory-bank/ is missing, treat the repository root as <target-repo> unless the operator supplied another target. Accept <devrails-checkout> only when supplied by the operator or already verifiable by its scripts/install-framework.mjs.

When both paths are known, return this command with shell-safe resolved paths:

node <devrails-checkout>/scripts/install-framework.mjs --bootstrap --target <target-repo> --yes

Otherwise ask for the checkout path and stop. Do not call /mb-init, run local bootstrap logic, copy helpers, install dependencies, or create the skeleton. After external bootstrap, rerun /start.

When .memory-bank/ exists, read .memory-bank/index.md, .memory-bank/workflows/execute-loop.md#interactive-mode-you-stay, and only the product, PRD, baseline, spec/foundation, feature, task, review, protocol, or handoff records needed to resolve the current incomplete boundary. File existence and conversation memory are not workflow state; use authoritative statuses, verdicts, Planning Revision, dependencies, and durable handoffs. </input_contract>

<hard_invariants>

/start writes no artifact or lifecycle state; the selected skill owns its mutations and handoff.
Select no unattended mode without an explicit operator instruction.
Do not create roadmap or task state without a clarified PRD/delta.
Do not bypass an existing review, Foundation, dependency, doctor, tier, or operator-decision gate.
Do not choose among multiple eligible features or tasks without an authoritative target. </hard_invariants>

<routing_contract> Prefer a valid unfinished durable handoff or resume route. Otherwise select the first incomplete boundary in the interactive execute-loop whose prerequisites are satisfied. Substantial existing code without a current evidence-backed baseline routes to /map-codebase before new product planning.

Invoke the one selected owning skill and stop routing. If the owner or target depends on an unresolved operator choice, ask that one question and stop. Do not output or execute a downstream chain. </routing_contract>

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 · 66 lines · 32 tokens per session scan A 48dbce500526

Subscribe to this mod's changes

start is a command published in the GitHub repository nicelight/DevRails-26 (22 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 582 once invoked, about $0.0002 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

start

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/start — Resolve next workflow owner

What this file has done since we first saw it

Other commands, from other repositories

git

checklist

clarify

specify

analyze

constitution