goal-flight CLAUDE.md

goal-flight CLAUDE.md is an instructions file for Claude Code from simonrowland/goal-flight. It costs 155 tokens per session, scanned A, original, MIT.

Safety instructions for keeping certain internal trigger names out of a project’s visible Git records. Git records include filenames, branches, tags, commits, and history.

In plain words
What is it for?
Use them when handling installer aliases, JSON manifests, legacy packages, commits, branches, or any other Git-visible project metadata.
Why use it?
They prevent sensitive names from being exposed accidentally while installing or moving older packages.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions 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 instructions/simonrowland/goal-flight/claude-md
Clone the repo
git clone --depth 1 https://github.com/simonrowland/goal-flight

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 goal-flight CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/simonrowland/goal-flight/claude-md.svg)](https://agentmods.dev/instructions/simonrowland/goal-flight/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/simonrowland/goal-flight/claude-md"><img src="https://agentmods.dev/badge/instructions/simonrowland/goal-flight/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 155 This file is loaded in full into every session.
When invoked 155 The same file — it is already loaded in full.
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 5.1 $0.00155 $0.00155
Opus 5 $0.00077 $0.00077
Sonnet 5 $0.00031 $0.00031
Haiku 4.5 $0.00015 $0.00015

Measured 6d ago against content hash bbd31f8a86fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

goal-flight CLAUDE.md 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 6d 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.md · 14 lines

What it actually says

Claude Code Notes

Git-Visible Trigger Hygiene

  • Never put the known billing-trigger harness codenames from this thread in git-visible metadata: filenames, directories, branch names, tag names, commit messages, generated JSON manifest names, or installer output paths.
  • Do not repeat those exact codenames in this file. Claude Code reads this file.
  • Installer aliases must not become manifest filenames. If an installer command receives --agent=<trigger-codename>, map that alias to a neutral manifest filename before reading or writing adapters/*.json.
  • When porting legacy packages, rename codename JSON manifests before staging, then run the trigger audit against status, paths, commit messages, and history.
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. 6d ago First seen · 14 lines · 155 tokens per session scan A bbd31f8a86fe

Subscribe to this mod's changes

goal-flight CLAUDE.md is an instructions file published in the GitHub repository simonrowland/goal-flight (20 stars, last pushed yesterday), licensed MIT. It adds 155 tokens to every session, about $0.0008 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.