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/afar1/fieldtheory-cli/claude-mdgit clone --depth 1 https://github.com/afar1/fieldtheory-cliWrote 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/afar1/fieldtheory-cli/claude-md)<a href="https://agentmods.dev/instructions/afar1/fieldtheory-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/afar1/fieldtheory-cli/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 | $0.00610 | $0.00610 |
| Opus 5 | $0.00305 | $0.00305 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
fieldtheory-cli 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This is the Field Theory CLI: a local-first command-line companion for X bookmark sync, Field Theory Library workflows, portable commands, app install, and agent-facing context.
Commands
npm run build # Compile TypeScript to dist/
npm run dev # Run via tsx directly
npm run test # Run tests
npm run start # Run compiled dist/cli.js
Architecture
Single CLI application built with Commander.js. Bookmark data is stored in ~/.fieldtheory/bookmarks/; Library markdown is stored in ~/.fieldtheory/library/; portable commands live under ~/.fieldtheory/commands/; and Possible run artifacts live under ~/.fieldtheory/ideas/.
Key files
| File | Purpose |
|---|---|
src/cli.ts |
Command definitions, progress bar, first-run UX |
src/paths.ts |
Data, library, and commands path resolution |
src/graphql-bookmarks.ts |
GraphQL sync engine (Chrome session cookies) |
src/bookmarks.ts |
OAuth API sync |
src/bookmarks-db.ts |
SQLite FTS5 index, search, list, stats |
src/bookmark-classify.ts |
Regex-based category classifier |
src/bookmark-classify-llm.ts |
Optional LLM classifier |
src/bookmarks-viz.ts |
ANSI terminal dashboard |
src/chrome-cookies.ts |
Chrome cookie extraction (macOS Keychain) |
src/xauth.ts |
OAuth 2.0 flow |
src/db.ts |
WASM SQLite layer (sql.js-fts5) |
src/library.ts |
Local Field Theory Library read/write helpers |
src/commands-files.ts |
Portable command file creation and validation |
src/app-open.ts |
Open Library pages in the packaged Mac app or a dev checkout |
src/app-install.ts |
Download and install packaged app releases |
src/skill.ts |
Install Field Theory agent skills for Claude Code and Codex |
src/ideas.ts |
Possible seeds, runs, jobs, and nightly schedules |
Data flow
Chrome cookies → GraphQL API → JSONL cache → SQLite FTS5 index
↓
Regex classification
↓
Search / List / Viz
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 · 66 lines · 610 tokens per session scan A 2612609c4d64
fieldtheory-cli CLAUDE.md is an instructions file published in the GitHub repository afar1/fieldtheory-cli (2,018 stars, last pushed 14d ago), licensed MIT. It adds 610 tokens to every session, about $0.0030 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
siyuan AGENTS.md
AGENTS.md instructions for siyuan-note/siyuan, covering agents.md, 1. non-negotiable constraints, do not hand-edit, verification and prohibited operations and 2. project-specific rules.
neurostack CLAUDE.md
Instructions for raphasouthall/neurostack, covering neurostack - claude code guide, quick reference, installation, mcp server (recommended for claude code) and openai-compatible api.
my-wiki AGENTS.md
Instructions for NimaChu/my-wiki, covering my wiki agent project, project map, knowledge model, route requests and development checks.
Siftly CLAUDE.md
Instructions for viperrcrypto/Siftly, covering siftly, quick setup, ai authentication — no api key needed, key commands and project structure.
Knote AGENTS.md
Instructions for 1661169091kiwi/Knote, covering agents.md, 构建与验证约定（用户明确要求，所有会话必须遵守） and 测试说明.
nexusos AGENTS.md
Instructions for asimons81/nexusos, covering agents.md, mission, isolation rules, architecture boundary and current release boundary.