anchor: Instructions file for Claude Code

CLAUDE.md

anchor CLAUDE.md is an instructions file for Claude Code from myrddian/anchor. It costs 1,543 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Anchor, a Spring Boot service that checks whether document passages support a question. Spring Boot is a framework for building Java web services.

In plain words
What is it for?
Use them when working on document validation, hierarchical summaries, the validation API, document questions, or streamed deliberation.
Why use it?
They give the agent the project’s required architecture and layering rules before making changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is myrddian/anchor's own configuration. It tells Claude Code how to work on anchor 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 anchor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to myrddian/anchor. 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/myrddian/anchor/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/myrddian/anchor

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 anchor CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/myrddian/anchor/claude-md.svg)](https://agentmods.dev/instructions/myrddian/anchor/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/myrddian/anchor/claude-md"><img src="https://agentmods.dev/badge/instructions/myrddian/anchor/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,543 This file is loaded in full into every session.
When invoked 1,543 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 $0.01543 $0.01543
Opus 5 $0.00772 $0.00772
Sonnet 5 $0.00309 $0.00309
Haiku 4.5 $0.00154 $0.00154

Measured 8d ago against content hash 025590527c6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

anchor 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.

CLAUDE.md · 66 lines

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.

Anchor — agent orientation

SPEC.md is the source of truth for v0. Read it before any non-trivial work. This file is the high-signal index, not a substitute.

What this is

A Spring Boot service exposing one primitive — source-grounded chunk validation — through two interfaces optimised for different consumers:

  • POST /validateLLM-to-LLM. Synchronous, deterministic JSON judgment about whether a chunk is load-bearing for a query, given the document's full argument. Enums (argumentative_role, document_stance_on_query), short reasoning, machine-parseable.
  • POST /documents/{id}/askhuman-facing. Async three-agent deliberation (proposer → critic → synthesiser) with differentiated evidence access (proposer/synthesiser see full hierarchy, critic sees macro view only). SSE-streamed token-by-token. The deliberation is the trust mechanism, not theatre.

Both back onto the same hierarchical claim-bearing summarisation: documents → chapters → sections → paragraphs → chunks, summaries at every level, embeddings on chunks. The critical compression rule: raw text never appears in inputs to layers above paragraph summarisation (SPEC §4.5).

Mental model: documents-as-databases. Each ingested document is the unit of query (analogous to psql connecting to one DB on a multi-DB server). Cross-corpus retrieval exists but is the exception. The "select a document, then query it" UX lives in the client; the server is stateless apart from the in-memory job store for in-flight /ask deliberations.

Stack

Java 21, Spring Boot 3.3.x, Gradle (Kotlin DSL), Spring Data JPA + Hibernate, Postgres 16 + pgvector (768-dim, HNSW cosine), Apache PDFBox 3.x, hand-rolled OkHttp+Jackson client against LM Studio's OpenAI-compatible API, Spring Shell for the demo harness, MapStruct for mapping, Flyway for migrations, JUnit 5 + Testcontainers + Mockito. Apache 2.0 + NOTICE.

LM Studio runs on a separate Mac Studio over LAN. Chat: Gemma 4 E4B. Embedding: nomic-embed-text-v1.5.

Read the full file on GitHub · 66 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. 8d ago First seen · 66 lines · 1,543 tokens per session scan A 025590527c6d

Subscribe to this mod's changes

anchor CLAUDE.md is an instructions file published in the GitHub repository myrddian/anchor (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,543 tokens to every session, about $0.0077 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 · 5,153 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