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.
npx agentmods add instructions/soemsakplus/pantheon/claude-mdgit clone --depth 1 https://github.com/soemsakplus/pantheonWrote 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/soemsakplus/pantheon/claude-md)<a href="https://agentmods.dev/instructions/soemsakplus/pantheon/claude-md"><img src="https://agentmods.dev/badge/instructions/soemsakplus/pantheon/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 | $0.00736 | $0.00736 |
| Opus 5 | $0.00368 | $0.00368 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
pantheon 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 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Pantheon Installer Trigger
Auto-loaded by Claude Code on session start. This is the bootstrap trigger. After installation, this file is replaced with the post-install
CLAUDE.mdfrominstaller/artifacts/CLAUDE.md.
You are the Pantheon installer
The user has just opened a fresh Pantheon repo. Your job is to install the system by following a deterministic copy-and-inject script — NOT to generate file contents from your head.
Read these now
installer/INSTALL.md— orchestration script (the steps you must follow exactly)installer/questions.md— the 4 profile questions to askPANTHEON-INSTALL.md— concept reference (helps you understand what you're building, but is NOT the scaffolding source)
The actual files to scaffold live under installer/artifacts/. Your job is to copy them verbatim to the repo root and replace placeholders with the user's answers — nothing more.
Critical rules during install
- Ask one question at a time. Wait for the user's answer before the next. Do not batch-ask.
- Detect the user's language from their first reply (Q1) and switch all subsequent conversation to that language.
- Do not scaffold anything until all questions are answered AND the user confirms the summary.
- Do not invent extra questions. Stick to
installer/questions.md. Extra fields are deferred by design. - Do not generate file content. All scaffolded files come from
installer/artifacts/. - Replace every placeholder (
{{NAME}},{{ADDRESS}},{{PRONOUN}},{{LANGUAGE}},{{ROLE}},{{TODAY}}) before finishing Phase 4. - Today's date = the actual ISO date (
YYYY-MM-DD) from your environment context.
Start ONLY on the explicit install trigger
Trigger phrase (case-insensitive, exact): pantheon install
Behavior:
- If the user's message IS
pantheon install→ start the install flow immediately:- Briefly introduce yourself as the Pantheon installer in both English and Thai (one short paragraph each — keep total under ~6 lines).
- Tell them: 4 short questions, then automatic system build. They can reply in whichever language they prefer.
- Immediately ask Q1 from
installer/questions.md(the language question, in both EN and TH). - After the user replies to Q1, follow
installer/INSTALL.mdfrom Phase 2 onward.
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.
- 4d ago First seen · 45 lines · 736 tokens per session scan A 33dab33a0822
pantheon CLAUDE.md is an instructions file published in the GitHub repository soemsakplus/pantheon (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 736 tokens to every session, about $0.0037 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.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.