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/frkdrgt/ferox/claude-mdgit clone --depth 1 https://github.com/frkdrgt/feroxWrote 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/frkdrgt/ferox/claude-md)<a href="https://agentmods.dev/instructions/frkdrgt/ferox/claude-md"><img src="https://agentmods.dev/badge/instructions/frkdrgt/ferox/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 5.1 | $0.02284 | $0.02284 |
| Opus 5 | $0.01142 | $0.01142 |
| Sonnet 5 | $0.00457 | $0.00457 |
| Haiku 4.5 | $0.00228 | $0.00228 |
Grade A, and why
ferox 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pgclient — CLAUDE.md
Proje Özeti
Hafif bir masaüstü PostgreSQL client uygulaması. Rust + egui/eframe ile yazılmış. Hedef: DBeaver/DataGrip'e alternatif, <50MB RAM, <200ms startup.
Gerçek ölçümler (v0.2.3): ~45–47 MB RAM, 6.9 MB binary (release LTO)
Tech Stack
- GUI: egui 0.27 + eframe (immediate-mode, pure Rust;
accesskitdevre dışı) - DB Driver: tokio-postgres 0.7 (async, pure Rust;
simple_querytext protokol) - Async: tokio (current-thread runtime, ayrı std::thread içinde)
- TLS: native-tls + postgres-native-tls
- SSH: russh 0.44
- Config: serde + toml
- Export: serde_json + manuel CSV
- File Dialog: rfd 0.14 (native OS diyaloğu)
- SQL Highlighting: sıfırdan yazılmış tokenizer —
src/ui/syntax.rs(syntect yok) - i18n: sıfırdan yazılmış —
src/i18n.rs(sıfır bağımlılık)
Mimari — Kritik Kural
UI thread (eframe) ↔ DB thread arası haberleşme SADECE mpsc kanalları ile:
Sender<DbCommand>→ UI'dan DB'ye komutSender<DbEvent>→ DB'den UI'a sonuç- DB thread kendi
current_threadtokio runtime'ınıstd::thread::spawniçinde oluşturur spawn_blockingile sync recv, sonra async tokio-postgres
Bu pattern'i ASLA değiştirme. eframe main thread'i bloke eden hiçbir şey yapma.
Modül Yapısı
src/
├── main.rs — eframe init, current_thread tokio runtime
├── app.rs — PgClientApp, eframe::App impl, event loop
├── config.rs — ConnectionProfile, AppConfig (TOML)
├── history.rs — QueryHistory (kalıcı, max 500)
├── snippets.rs — Saved queries (Ctrl+Shift+S, name+SQL, TOML-persisted)
├── i18n.rs — Lang enum (En|Tr), I18n(pub Lang) newtype, ~100+ method
├── logger.rs — crash log (panic hook)
├── db/
│ ├── mod.rs
│ ├── connection.rs — DbCommand/DbEvent, db_worker, execute_query (simple_query)
│ ├── query.rs — CellValue enum, QueryResult
│ ├── metadata.rs — Schema/table/column/index/FK introspection
│ └── ssh.rs — SSH tunnel (russh)
└── ui/
├── mod.rs
├── sidebar.rs — SidebarAction, schema tree, context menu
├── query_panel.rs — SQL editör, BrowseState, sayfalama
├── result_table.rs — egui_extras::TableBuilder, sort, inline edit
├── tab_manager.rs — Tab lifecycle, yönlendirme, sağ-tık menüsü
├── connection_dialog.rs
├── dashboard.rs — DB dashboard (tablo boyutları, bağlantılar, index)
├── explain.rs — EXPLAIN ANALYZE ağaç görünümü
├── er_diagram.rs — ER diyagramı
├── autocomplete.rs — Tablo/sütun otomatik tamamlama
└── syntax.rs — Sıfırdan SQL tokenizer (keyword/type/string/comment)
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.
- 5d ago First seen · 141 lines · 2,284 tokens per session scan A 50107dc0f4fe
ferox CLAUDE.md is an instructions file published in the GitHub repository frkdrgt/ferox (86 stars, last pushed 2mo ago), licensed MIT. It adds 2,284 tokens to every session, about $0.0114 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 2026-08-30.
Other instructions, from other repositories
turso AGENTS.md
AGENTS.md instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
prest copilot-instructions.md
Copilot instructions for prest/prest, covering copilot instructions for prest go backend, project scope, core engineering principles, solid principles for go and s — single responsibility.
dynoxide AGENTS.md
AGENTS.md instructions for nubo-db/dynoxide, covering agents.md, what dynoxide is, ground rules for contributions, rust conventions and testing expectations.
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
epistemic-graph AGENTS.md
Instructions for Knuckles-Team/epistemic-graph, covering agents.md — epistemic graph compute engine, epistemic os surfaces in the main build, commands for ai agents, python api (out-of-process client — not in-process) and async.
hash rust-review.instructions.md
Review guidance for Rust changes.