preflight

preflight is a skill for Claude Code, Codex from travisennis/acai. It costs 68 tokens per session (2,216 once invoked), scanned A, original, MIT.

A final review workflow for an almost finished code change. It adjusts the review effort to the size of the change and checks rules, correctness, source information, and unnecessary complexity.

In plain words
What is it for?
Use it after a feature works to review the diff, related task details, repository rules, and readiness for commit or handoff.
Why use it?
It catches worthwhile issues before a commit or handoff while keeping the final change as small and clear as possible.

Skill for Claude CodeCodex

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 skills/travisennis/acai/preflight
Any agent
npx skills add travisennis/acai --skill preflight
Clone the repo
git clone --depth 1 https://github.com/travisennis/acai

Made for: Claude Code, Codex.

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/skills/travisennis/acai/preflight.svg)](https://agentmods.dev/skills/travisennis/acai/preflight)
Your own site
<a href="https://agentmods.dev/skills/travisennis/acai/preflight"><img src="https://agentmods.dev/badge/skills/travisennis/acai/preflight.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,216 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 $0.00068 $0.02216
Opus 5 $0.00034 $0.01108
Sonnet 5 $0.00014 $0.00443
Haiku 4.5 $0.00007 $0.00222

Measured 4d ago against content hash ed956a235a8e, 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 4d 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.

.agents/skills/preflight/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Preflight

Use this skill after a change is functionally correct and before commit or handoff. The PR, commit text, task notes, and final response should describe already-preflighted code.

Goals

Leave the smallest clear diff that still solves the issue. Run focused review passes instead of one subjective read. Preserve behavior while improving readability, correctness, and alignment with repo rules.

Scale the review to the change size

Pick an effort level from the diff before reading anything else:

git diff --stat
git status --short

Include untracked new files from git status --short (or git ls-files --others --exclude-standard) when choosing the scale. A split into new files can look deceptively small in git diff --stat until those files are staged.

Change size Required context Review passes Compliance note
XS (docs/skill/config only, ≤2 files) Root AGENTS.md if relevant One combined pass One line
S (single module, ≤~50 LOC, no public API) Root AGENTS.md, nearest nested AGENTS.md One combined pass One line
M (multi-file, ≤~200 LOC, no cross-module) + active task file, ExecPlan if one exists Pass 1 + Pass 2 Short block
L/XL (cross-module, public API, agent loop, persistence, concurrency, external integrations, security boundaries) + design docs and ADRs in the changed area All three passes Full block

Only read context items that are relevant to the changed surface. Discover them with targeted commands, e.g. rg --files -g AGENTS.md, rg --files docs/design-docs docs/adr, git diff -- <paths>.

Required context items, in priority order:

  • repo root AGENTS.md
  • nested AGENTS.md files for the changed areas
  • ahm context task, ahm task show <id> output when the work came from a task; open the active task file only when ahm is unavailable or when reviewing manual edits to the task file itself; use .agents/.tasks/index.md only as a fallback queue artifact when ahm is unavailable
  • the relevant active exec plan when one exists for the current work (see .agents/exec-plans/active/)
  • ahm context plan and docs/design-docs/index.md for L/XL changes
  • any design doc or ADR directly relevant to the changed area
  • the changed files and enough nearby context to review them

Read the full file on GitHub · 224 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. 4d ago First seen · 224 lines · 68 tokens per session scan A ed956a235a8e

Subscribe to this mod's changes

preflight is a skill published in the GitHub repository travisennis/acai (5 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 2,216 once invoked, about $0.0003 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 2026-08-31.