Borrowing it
Nothing to install: this file belongs to jame581/GodotPrompter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jame581/GodotPrompter/master/CLAUDE.mdgit clone --depth 1 https://github.com/jame581/GodotPrompterWrote 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.
[](https://agentmods.dev/instructions/jame581/godotprompter/claude-md)<a href="https://agentmods.dev/instructions/jame581/godotprompter/claude-md"><img src="https://agentmods.dev/badge/instructions/jame581/godotprompter/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.01613 | $0.01613 |
| Opus 5 | $0.00807 | $0.00807 |
| Sonnet 5 | $0.00323 | $0.00323 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
GodotPrompter 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GodotPrompter — Contributor Guidelines
Project Overview
This is a documentation/skills repository. There is no application build/lint, but node scripts/validate-skills.mjs checks SKILL.md frontmatter, cross-references, and structure — it runs in CI on every release tag. Otherwise, changes are validated by reading skills, verifying code examples in Godot 4.3+, and running the agent integration tests in tests/agent-integration/TEST_PLAN.md.
Supported Platforms
- Claude Code (primary — tool names are canonical)
- GitHub Copilot CLI
- Antigravity (IDE +
agyCLI) — succeeds Gemini CLI, which Google retired on 2026-06-18 - Codex
- Cursor
- OpenCode
- Grok Build
Conventions
- Skills use Claude Code tool names as the canonical reference
- Each platform has a tool mapping file in
skills/using-godot-prompter/references/ - GDScript follows the Godot style guide — snake_case functions/variables, PascalCase classes
- C# follows Godot C# conventions — PascalCase methods matching the Godot API
- Target Godot 4.3+ minimum — no deprecated methods
Skill Authoring
- Skills must be self-contained and independently useful
- Include both GDScript and C# examples where applicable
- Test skills against real Godot projects before merging
Repository Rules
The layout is self-evident from ls; these constraints are not:
- SKILL.md size: keep under 16 KB.
validate-skills.mjserrors at ≥ 16 KB (fails CI) and warns at ≥ 15.5 KB. Overflow goes inreferences/as load-on-demand deep dives (Pattern X). - Version lockstep:
release.ymlverifies five files —package.json, the rootplugin.json(Antigravity),.claude-plugin/plugin.json,.claude-plugin/marketplace.json, and.cursor-plugin/plugin.json.scripts/bump-version.mjs <version>updates all five and syncs the skill-count description. - Two hook directories:
hooks/(root) ships to plugin users — the SessionStart routing card.scripts/hooks/is repo development tooling wired via.claude/settings.json, which runsvalidate-skill-on-edit.mjsafter every Edit/Write. Never merge them. - Card regions:
using-godot-prompter(SESSION-CARD) andgodot-mentor(MENTOR-CARD) contain marker-delimited regions the hook injects verbatim.validate-skills.mjsenforces markers, uniqueness, non-emptiness, and a 3 KB cap. Edit the region, never a copy — and never paste the marker strings into a fenced example, which tripscard-marker-duplicate. - The hook does not reach subagents.
SessionStartfires on startup/resume/clear/compact only. A## GodotPromptersection in the project's agent instructions file is what subagents read. The offer to add one probes every file a supported host loads (CLAUDE.md,AGENTS.md,GEMINI.md,.github/copilot-instructions.md, the rules directories) and is suppressed for good by"section_offer": "declined"in the project's~/.godot-prompter/state/file — probing one filename nagged agent-agnostic repos forever (#15). The probe is deliberately host-agnostic: a section in any of those files silences the offer on every host, trading a subagent that may stay uninstructed on a host that does not read that file against nagging a repo that has already documented the rule. - Hook changes require
npm run test:hooks.node --test tests/hooks/does not work on Node 24 — a directory argument is imported as a module. AGENTS.md/GEMINI.mdare root @-imports that re-exportusing-godot-prompterfor Codex and Antigravity — edit the skill, not these.- Agents are mirrored, not shared. Each
agents/<name>.mdhas a hand-maintained twin at.codex/agents/godot-prompter/<name>.toml. The validator walksagents/*.mdonly, so drift is silent — edit both. .github/workflows/release.ymlis tag-triggered: it validates, creates the GitHub release, and opens marketplace PRs.docs/superpowers/notes/holds per-release research notes and the C# parity debt list.
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.
- 8d ago First seen · 73 lines · 1,613 tokens per session scan A 900fdca0900a
GodotPrompter CLAUDE.md is an instructions file published in the GitHub repository jame581/GodotPrompter (677 stars, last pushed 26d ago), licensed MIT. It adds 1,613 tokens to every session, about $0.0081 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.