jrag CLAUDE.md

Project-specific working rules for jrag, a Python project, covering its environment, tests, documentation, and shipped files. They specify which local executables and test practices contributors should use.

In plain words
What is it for?
Use them when developing or testing jrag, updating its documentation, installing it in editable mode, or checking generated and compatibility files.
Why use it?
They prevent common project mistakes, such as using the wrong Python environment, keeping stale test indexes, or changing compatibility names that are intentional. They also distinguish operator documentation from contributor documentation.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/humanbean17/jrag/claude-md
Clone the repo
git clone --depth 1 https://github.com/HumanBean17/jrag
Per session 767 This file is loaded in full into every session.
When invoked 767 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
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 $0.00767 $0.00767
Opus 5 $0.00383 $0.00383
Sonnet 5 $0.00153 $0.00153
Haiku 4.5 $0.00077 $0.00077

Measured 3d ago against content hash 673a08304bd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

jrag CLAUDE.md scanned grade C with 1 finding 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 3d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

`rm -rf tests/*/.java-codebase-rag tests/*/.java-codebase-rag.{yml,hosts}`
CLAUDE.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

jrag

Python environment

Use .venv/bin/python and .venv/bin/pip (repo root) for all Python commands. Invoke the .venv/bin executables directly — never system python/pip.

Editable install only. If jrag/java-codebase-rag serve stale behavior while pytest passes, run .venv/bin/pip install -e ".[dev]" — don't report it. tests/conftest.py enforces this.

Tests

  • Erase stale manual indexes first — they hijack project-root discovery: rm -rf tests/*/.java-codebase-rag tests/*/.java-codebase-rag.{yml,hosts}
  • Tests build their own fresh index in a temp dir; never commit one under tests/ (.gitignore un-ignores it there).
  • The full suite is slow. Run only the subset relevant to your change during development; run the full suite once, at the end of the task.
  • On-disk .java-codebase-rag* names (index dir, project YAML, hosts) and JAVA_CODEBASE_RAG_* env vars are intentionally retained for backward compatibility — do not "fix" them.

Docs

Most files in docs/ are operator-facing. The two flagged below are internal (contributor) docs.

Operator docs

  • docs/CONFIGURATION.md — env vars, project YAML, ontology, brownfield overrides, ignore patterns.
  • docs/JRAG-CLI.md — operator CLI playbook (workflows, exit codes, env alignment).
  • docs/MIGRATION.mdjava-codebase-ragjrag rename map (commands, package, untouched on-disk state).
  • docs/AGENT-GUIDE.md — agent-facing MCP operating manual (copy-paste into AGENTS.md/CLAUDE.md).
  • docs/EDGE-NAVIGATION.md — MCP-traversable edges, directions, dot-key composition.
  • docs/MANUAL-VERIFICATION-CHECKLIST.md — 7-phase post-index verification.
  • docs/CODEBASE_REQUIREMENTS.md — assumptions about the target Java repo.
  • docs/PRODUCT-VISION.md — long-term product direction.
  • docs/paper/paper.pdf — architecture report (rationale, GPS metaphor, ontology).

Internal docs (contributors working on this repo)

  • docs/DESIGN.md — WHAT/WHY: core principles, what's indexed, surfaces, non-goals.
  • docs/ARCHITECTURE.md — HOW: pipeline, module map, write/read paths, stores, extension points.

Read the full file on GitHub · 58 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. 3d ago First seen · 58 lines · 767 tokens per session scan C 673a08304bd6

Subscribe to this mod's changes

jrag CLAUDE.md is an instructions file published in the GitHub repository HumanBean17/jrag (9 stars, last pushed 8d ago), licensed MIT. It adds 767 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.