preflight

preflight is a command for Claude Code from nimble-giant/ailloy. It costs 0 tokens per session (517 once invoked), scanned A, original, Apache-2.0.

A command for planning a new coding task or short development project before implementation begins. It reviews the request, checks whether it is well defined, and outlines acceptance criteria and a possible design.

In plain words
What is it for?
Use it to analyze an issue, decide whether it is ready to build, define measurable outcomes, and sketch a test or design approach.
Why use it?
It helps expose unclear requirements, missing edge cases, and uncertain success conditions before coding starts.

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/nimble-giant/ailloy/preflight
Clone the repo
git clone --depth 1 https://github.com/nimble-giant/ailloy

Made for: Claude Code.

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.

agentmods badge for preflight

README.md
[![agentmods](https://agentmods.dev/badge/commands/nimble-giant/ailloy/preflight.svg)](https://agentmods.dev/commands/nimble-giant/ailloy/preflight)
Your own site
<a href="https://agentmods.dev/commands/nimble-giant/ailloy/preflight"><img src="https://agentmods.dev/badge/commands/nimble-giant/ailloy/preflight.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 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 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 $0.00000 $0.00517
Opus 5 $0.00000 $0.00259
Sonnet 5 $0.00000 $0.00103
Haiku 4.5 $0.00000 $0.00052

Measured 5d ago against content hash cb359099c1fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

preflight 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 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.

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/preflight.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

preflight

Run pre-flight planning for a new task or mini-sprint.

Usage

claude preflight
claude preflight <issue-number>

Description

Executes the Pre-Flight Planning ceremony to ensure proper understanding and alignment before starting implementation.

Important: When this command is invoked, Claude should immediately switch to plan mode to properly analyze and plan the task before any implementation begins.

Steps

First: Enter plan mode to properly analyze the task. This ensures thoughtful planning before implementation.

  1. Read & Clarify

    • Read the issue aloud
    • Capture domain language and user intent
    • Identify key requirements
  2. INVEST Check Evaluate the task against INVEST criteria:

    • Independent
    • Negotiable
    • Valuable
    • Estimable
    • Small
    • Testable
  3. Acceptance Criteria

    • Express as BDD specs (Given/When/Then format)
    • Ensure measurable outcomes
    • Cover edge cases
  4. Design Sketch If helpful, propose a light design:

    • Mermaid diagram for architecture
    • Bullet points for data flow
    • Test strategy outline
  5. Go/No-Go Decision

    • Present findings for approval
    • Request refinement if needed

Example Output

## Pre-Flight Analysis: Issue #123

### INVEST Evaluation
- ✅ Independent: Can be completed without other tickets
- ✅ Negotiable: Scope can be adjusted
- ✅ Valuable: Delivers user value
- ✅ Estimable: ~2 days effort
- ✅ Small: Fits in one sprint
- ✅ Testable: Clear pass/fail criteria

### Acceptance Criteria
```gherkin
Given a user has admin privileges
When they navigate to the settings page
Then they should see the "Export Data" button

Given a user clicks "Export Data"
When the export completes
Then they receive a downloadable CSV file

Design Sketch

  • New endpoint: GET /api/export/data
  • Service layer: DataExportService
  • Test approach: Unit tests for service, integration for endpoint

Ready for go/no-go decision.

Read the full file on GitHub · 88 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. 5d ago First seen · 88 lines · 0 tokens per session scan A cb359099c1fc

Subscribe to this mod's changes

preflight is a command published in the GitHub repository nimble-giant/ailloy (10 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 517 tokens. 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 2026-08-31.