codebeacon CLAUDE.md

Instructions for finding information in a repository using a pre-built CodeBeacon index, Obsidian notes, and source files. A repository is the project's stored code and related files.

In plain words
What is it for?
Use it when answering where code is located or tracing how parts of a project connect: check the CodeBeacon wiki, then notes, then the source files, with direct search as a fallback.
Why use it?
It gives coding agents an ordered way to locate routes, controllers, services, entities, and other code without searching the entire project first.

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/wandererer/codebeacon/claude-md
Clone the repo
git clone --depth 1 https://github.com/Wandererer/codebeacon
Per session 594 This file is loaded in full into every session.
When invoked 594 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00594 $0.00594
Opus 5 $0.00297 $0.00297
Sonnet 5 $0.00119 $0.00119
Haiku 4.5 $0.00059 $0.00059

Measured 2d ago against content hash 17f640fa17b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebeacon 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 2d 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 · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Lookup strategy

This repo ships a pre-built index in .codebeacon/. Check it first — most "where is X" questions resolve in one read without a full-repo search.

Repo type: single — Single-project repo.

Step 1 — codebeacon wiki

Routes, controllers, services, entities.

.codebeacon/wiki/index.md                    ← global index
.codebeacon/wiki/{project}/controllers/{Name}.md  ← controller logic
.codebeacon/wiki/{project}/services/{Name}.md     ← service methods
.codebeacon/wiki/{project}/entities/{Name}.md     ← data models
.codebeacon/wiki/routes.md                   ← all API routes across projects

Step 2 — obsidian notes

Class-level detail (methods, fields, incoming/outgoing edges) the wiki omits. Look up by class name — replace {project} with the relevant folder:

.codebeacon/obsidian/{project}/{ClassName}.md
Project Notes Example
codebeacon 413 services, 3 entities affected_from_paths.py.md

Step 3 — source file

Open the paths surfaced by Steps 1–2.

Fall back to direct search

Reach for Glob, Grep, or the Explore agent when the index does not cover what you need — new files, deep implementation details, or cross-cutting searches that span projects.


Projects

Project Framework Routes Services Entities Components
codebeacon python 5 413 3 0

Common Commands

codebeacon (python)

# see project README  # build
# see project README  # run
# see project README  # all tests

Architecture

codebeacon: python · python Routes: 5 | Services: 413 | Entities: 3 | Components: 0

High-Impact Files

Changes here affect many other files:

  • codebeacon/common/safety.py (imported by 9 files)
  • codebeacon/discover/detector.py (imported by 6 files)
  • codebeacon/wiki/generator.py (imported by 6 files)
  • codebeacon/affected.py (imported by 5 files)
  • codebeacon/common/symbols.py (imported by 5 files)

Read the full file on GitHub · 80 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. 2d ago First seen · 80 lines · 594 tokens per session scan A 17f640fa17b8

Subscribe to this mod's changes

codebeacon CLAUDE.md is an instructions file published in the GitHub repository Wandererer/codebeacon (2 stars, last pushed 1mo ago), licensed MIT. It adds 594 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 2026-08-31.