preflight

preflight is a command for coding agents from nguyenthienthanh/aura-frog. It costs 0 tokens per session (952 once invoked), scanned A, original, MIT.

A command for checking the current tool context, files, or commands against pre-flight safety policies, with an optional one-use bypass.

In plain words
What is it for?
It is for validating files, dry-running command checks, listing the seven safety checks, managing a single-use bypass, and viewing bypass status.
Why use it?
It catches policy, formatting, secret, or command-safety problems before another tool call runs.

Command

Part of the aura-frog plugin — 43 skills, 24 commands, 15 agents, 10 hooks, 6 MCP servers shipped together

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/nguyenthienthanh/aura-frog/preflight
Clone the repo
git clone --depth 1 https://github.com/nguyenthienthanh/aura-frog

Or install aura-frog, the plugin that ships this one along with the rest of its 43 skills, 24 commands, 15 agents, 10 hooks, 6 MCP servers.

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/nguyenthienthanh/aura-frog/preflight.svg)](https://agentmods.dev/commands/nguyenthienthanh/aura-frog/preflight)
Your own site
<a href="https://agentmods.dev/commands/nguyenthienthanh/aura-frog/preflight"><img src="https://agentmods.dev/badge/commands/nguyenthienthanh/aura-frog/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 952 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 $0.00952
Opus 5 $0.00000 $0.00476
Sonnet 5 $0.00000 $0.00190
Haiku 4.5 $0.00000 $0.00095

Measured 5d ago against content hash 82db44f4959e, 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.

aura-frog/commands/preflight.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aura-frog:preflight

Run pre-flight validation against the current tool context, manage policies, or bypass once.


Usage

/aura-frog:preflight check                            # run run-all.sh against current/last tool context
/aura-frog:preflight check --file path/to/file.md     # validate a specific file
/aura-frog:preflight check --command "<bash cmd>"     # dry-run a command's safety check
/aura-frog:preflight policies                         # list all 7 Tier 1 linters and what they check
/aura-frog:preflight bypass <reason>                  # disable next tool call's pre-flight (single use)
/aura-frog:preflight status                           # show bypass count this session + disabled state

Protocol — check

  1. Resolve target. With --file, validate the file (frontmatter, secret patterns). With --command, run command-allowlist on the string. Without args, use CLAUDE_TOOL_NAME + CLAUDE_TOOL_ARGS from env (the auto-hook context).
  2. Invoke bash aura-frog/scripts/preflight/run-all.sh with appropriate flags.
  3. Surface stderr (linter output) to user.
  4. Report aggregate exit code and per-check results.

Protocol — policies

Enumerate the Tier 1 scripts:

preflight policies (Tier 1 — bash, always-on):
  validate-frontmatter.sh    YAML frontmatter on plan/skill/agent/rule/command markdown
  validate-tool-input.sh     Tool input shape (required fields, absolute paths)
  validate-tool-output.sh    ANSI volume, prompt-injection phrases, JSON sanity
  check-path-safety.sh       Reject traversal + system files + credential dirs
  check-command-allowlist.sh Hard-block destructive; warn on risky
  check-secret-patterns.sh   AWS/GitHub/OpenAI/JWT/private-key patterns
  run-all.sh                 Orchestrator (returns max exit from above)

Tier 2 (OPA, optional): not yet shipped — deferred to v3.7.0-rc.1+

Protocol — bypass <reason>

Single-use override for the next tool call only. After consumption, normal pre-flight resumes.

Read the full file on GitHub · 82 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 · 82 lines · 0 tokens per session scan A 82db44f4959e

Subscribe to this mod's changes

preflight is a command published in the GitHub repository nguyenthienthanh/aura-frog (24 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 952 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 2026-08-30.