sophotron: Instructions file for Claude Code

CLAUDE.md

sophotron CLAUDE.md is an instructions file for Claude Code from rookslog/sophotron. It costs 2,011 tokens per session, scanned A, original, MIT.

A project guide for coding agents and developers working on Sophotron. It describes the project, where its code lives, its conventions, and how to build and verify changes.

In plain words
What is it for?
Use it to understand Sophotron’s architecture and philosophy-paper search system, follow coding conventions, and run the project’s build, test, and verification checks.
Why use it?
It gives unfamiliar contributors the context needed to make changes correctly and check whether they are complete.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Codex.

This is rookslog/sophotron's own configuration. It tells Claude Code how to work on sophotron itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sophotron configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rookslog/sophotron. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rookslog/sophotron/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/rookslog/sophotron

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 sophotron CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rookslog/sophotron/claude-md.svg)](https://agentmods.dev/instructions/rookslog/sophotron/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rookslog/sophotron/claude-md"><img src="https://agentmods.dev/badge/instructions/rookslog/sophotron/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,011 This file is loaded in full into every session.
When invoked 2,011 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.02011 $0.02011
Opus 5 $0.01006 $0.01006
Sonnet 5 $0.00402 $0.00402
Haiku 4.5 $0.00201 $0.00201

Measured 6d ago against content hash cdbace5c3011, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sophotron 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 · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Project Guide for Agents

This file orients an agent (or human) working on this repo: what it is, where things live, the conventions, and how to verify a change.

Parenthetical ids like (D-016) cite the maintainer's internal decision ledger. They annotate provenance for history's sake and are not resolvable from the public tree — the decision's substance is always restated where it matters.

What this is

Sophotron — an MCP server for philosophy-paper search/retrieval over four open sources — Semantic Scholar (backbone), OpenAlex + Unpaywall (open-access/PDF layer), and a cached PhilArchive OAI-PMH harvest. 18 MCP tools, TypeScript, @modelcontextprotocol/sdk + zod. Single-user, interactive research is the design target — not high-scale serving. (Name = sopho- "wisdom" + -tron "instrument"; MCP is the current interface, not the identity — the adapters/+services/ core never imports MCP, so a CLI or other frontend can be added over it without a refactor. See D-013. "PhilPapers/PhilArchive" still names the data source, not the product.)

Architecture (where things live)

  • src/index.ts — the MCP server frontend: registers all 18 tools, wires adapters→services→tools. Start here to understand the surface.
  • src/adapters/* — one module per external API (semantic-scholar, openalex, unpaywall, philarchive). Adapters own URL building, parsing, and per-source quirks. They never throw to callers: return {error} / null / [].
  • src/services/* — cross-source logic: crossref.ts (S2↔PhilArchive fuzzy matching + caches), pdf-resolver.ts (the OA fallback chain), and taxonomy-bridge.ts (the taxonomy→papers semantic bridge — lazy SPECTER2 category centroids + the category_id lens on search_papers/get_related + category_papers; D-016).
  • src/utils/http.tsshared fetchWithRetry (bounded exponential backoff + jitter on 429/5xx, Retry-After-aware, per-attempt timeout). New network calls should use it.
  • src/utils/fuzzy-match.ts — title/author similarity for DOI-less cross-referencing.
  • data/*.json — JSON caches (PhilArchive records, S2↔PhilArchive map). Resolved via SOPHOTRON_DATA_DIR or package-relative.

Read the full file on GitHub · 61 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. 6d ago First seen · 61 lines · 2,011 tokens per session scan A cdbace5c3011

Subscribe to this mod's changes

sophotron CLAUDE.md is an instructions file published in the GitHub repository rookslog/sophotron (0 stars, last pushed 4d ago), licensed MIT. It adds 2,011 tokens to every session, about $0.0101 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens