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/zuhabul/fetchium/claude-mdgit clone --depth 1 https://github.com/zuhabul/FetchiumWrote 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/zuhabul/fetchium/claude-md)<a href="https://agentmods.dev/instructions/zuhabul/fetchium/claude-md"><img src="https://agentmods.dev/badge/instructions/zuhabul/fetchium/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 | $0.02643 | $0.02643 |
| Opus 5 | $0.01321 | $0.01321 |
| Sonnet 5 | $0.00529 | $0.00529 |
| Haiku 4.5 | $0.00264 | $0.00264 |
Grade C, and why
Fetchium 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 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| GitHub Releases | `curl -sSf https://install.fetchium.com \| sh` | ✅ All 5 platforms | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| GitHub Releases | `curl -sSf https://install.fetchium.com \| sh` | ✅ All 5 platforms | How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build Commands
# Check all crates compile (fast, no linking)
cargo check
# Build the fetchium binary
cargo build -p fetchium-cli
# Build optimized release binary
cargo build -p fetchium-cli --release
# Run the binary
./target/debug/fetchium --help
./target/debug/fetchium doctor
# Run all tests
cargo test
# Run tests for a specific crate
cargo test -p fetchium-core
cargo test -p fetchium-cli
# Run a single test by name
cargo test -p fetchium-core extract::layer1::tests::extract_simple_page
# Lint (zero warnings policy — treat warnings as errors in CI)
cargo clippy -- -D warnings
# Format
cargo fmt
# Generate docs
cargo doc --open
macOS SDK Note
Xcode on this machine sometimes defaults to the iPhoneOS SDK, which breaks C dependency compilation (zstd-sys, rusqlite, ring). This is fixed in .cargo/config.toml which forces SDKROOT to the macOS SDK. If you see "architecture not supported" errors, run:
export SDKROOT=$(xcrun --sdk macosx --show-sdk-path)
Architecture Overview
Fetchium is a Cargo workspace with 4 crates:
| Crate | Role |
|---|---|
fetchium-core |
All algorithms: search, extract, rank, validate, cache, AI, intelligence |
fetchium-cli |
The fetchium binary — clap derive CLI, delegates everything to fetchium-core |
fetchium-mcp |
MCP server (Phase 4) — exposes fetchium-core as Model Context Protocol tools |
fetchium-api |
REST API server via axum (Phase 4) |
Data flow: CLI command → FetchiumConfig → fetchium-core pipeline → formatted output
The CLI (fetchium-cli/src/main.rs) parses args, loads config, then dispatches to one file per command in crates/fetchium-cli/src/commands/. Each command calls into fetchium-core modules.
fetchium-core Module Map
The retrieval pipeline is implemented across these modules. Foundational types/config:
types.rs— Shared data types:AgentSearchResult,SearchResult,ResultItem,Segment,Finding,Source,EvidenceGraph,CepLayer,PdsTier,ResourceTier,BackendId, etc.error.rs—FetchiumError,StructuredError,ErrorKind,FetchiumResult<T>config.rs—FetchiumConfigloaded from~/.fetchium/config.tomlwith env var overrides; includesdetect_resource_tier()anddata_dir()http/client.rs—HttpClient(reqwest with pooling/retries)resource/mod.rs—detect_tier()delegating toFetchiumConfig::detect_resource_tier()
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.
- 3d ago First seen · 232 lines · 2,643 tokens per session scan C f56878e39639
Fetchium CLAUDE.md is an instructions file published in the GitHub repository zuhabul/Fetchium (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 2,643 tokens to every session, about $0.0132 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
openfang AGENTS.md
AGENTS.md instructions for RightNow-AI/openfang, a project described as: Open-source Agent Operating System.
commonly CLAUDE.md
Claude Code instructions for Team-Commonly/commonly, covering claude.md / agents.md, 🧠 product vision & architecture philosophy, what commonly is, the architecture model and key concepts.
aci CLAUDE.md
Instructions for aipotheosis-labs/aci, covering claude.md, project overview, repository structure, essential development commands and backend commands.
ai-agent-automation AGENTS.md
AGENTS.md instructions for vmDeshpande/ai-agent-automation, covering agents.md, repo structure, dev commands, git hooks and code style.
Enclave AGENTS.md
Instructions for yuanzui0728/Enclave, covering 隐界app 项目规则, 规则, 技术栈与端口, 后端模块(api/src/modules/) and 主 app 结构(apps/app/src/).
openaccountants CLAUDE.md
Claude Code instructions for openaccountants/openaccountants, covering openaccountants — agent instructions, for ai agents landing here, repository overview, skill file conventions and audit flash point convention.