searcharvester CLAUDE.md

A set of project instructions for Claude Code, an AI coding assistant, covering a project called searcharvester. It describes the repository, its research system, and its three skills.

In plain words
What is it for?
Use it when working on searcharvester code, its research architecture, or its related skills.
Why use it?
It gives the coding assistant project-specific context so its changes and explanations match the repository.

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/vakovalskii/searcharvester/claude-md
Clone the repo
git clone --depth 1 https://github.com/vakovalskii/searcharvester
Per session 2,743 This file is loaded in full into every session.
When invoked 2,743 The same file — it is already loaded in full.
Security scan C 2 findings. Scan, not verified.
Origin unknown 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 $0.02743 $0.02743
Opus 5 $0.01372 $0.01372
Sonnet 5 $0.00549 $0.00549
Haiku 4.5 $0.00274 $0.00274

Measured yesterday against content hash 514a6dfe55e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

searcharvester CLAUDE.md scanned grade C with 2 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 yesterday.

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.

- **Изоляция agent ↔ adapter**: теперь в одном контейнере. Hermes `--yolo` terminal-команды выполняются в адаптерном user space. По сравнению с v2.1 (отдельный контейнер) — даунгрейд изоляции. Критично если кто-то скорми

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

5. Клиент (UI или curl) подписан на `/research/{id}/events` (SSE) — `orchestrator.subscribe()` отдаёт replay + live stream через ту же Condition
CLAUDE.md · 106 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. yesterday First seen · 106 lines · 2,743 tokens per session scan C 514a6dfe55e6

Subscribe to this mod's changes

searcharvester CLAUDE.md is an instructions file published in the GitHub repository vakovalskii/searcharvester (256 stars, last pushed 4mo ago), licensed AGPL-3.0. It adds 2,743 tokens to every session, about $0.0137 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories