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/covagashi/covaga.dev/claude-mdgit clone --depth 1 https://github.com/covagashi/covaga.devWrote 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/covagashi/covaga.dev/claude-md)<a href="https://agentmods.dev/instructions/covagashi/covaga.dev/claude-md"><img src="https://agentmods.dev/badge/instructions/covagashi/covaga.dev/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 | $0.01032 | $0.01032 |
| Opus 5 | $0.00516 | $0.00516 |
| Sonnet 5 | $0.00206 | $0.00206 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
covaga.dev 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — working rules for covaga.dev (Covaga Hub)
Instructions for any AI agent (and humans) working in this repository. This is a public, community project: keep it clean, typed, and well organized.
What this is
An open platform for EPLAN teams, built on Cloudflare. Two pillars:
- Data + Gym — ingest an article-database snapshot, then let an LLM close text gaps (translations, descriptions) through an MCP server whose validators are deterministic and server-side. Proposals are reviewed like pull requests; approved changes are written back to EPLAN by a local polling client.
- Automations — EPLAN events (PDF/BOM/project) routed to destinations (Microsoft Teams, email, webhook).
See ARCHITECTURE.md for the full map.
Design — NO AI SLOP (non-negotiable, top priority)
Using generic, invented, "AI-styled" UI is FORBIDDEN. Every screen must match the project's real, existing design — never improvise.
- The mockups are the source of truth. The owner designed the UI as HTML mockups
(in the
eplanbridgerepo,docs/mockups/). Build against them, pixel-for-intent. - The events / automations page is mockup
C3— "editor vertical (Zapier puro)": master–detail — the event list on the left; selecting an event shows its route as 3 vertical steps (1 Origen = the EPLAN.csscript, 2 Nexo = Covaga Hub, 3 Destinos). It is NOT a CRUD form. (Other mockups A/B/D and canvas variants were explicitly rejected.) - Reuse, never regenerate. If a screen already has a mockup or an existing implementation (e.g. the ported Covaga dashboard screens), port/match it exactly — do not redesign it.
- Brand: dark warm background, Signal Orange
#f26419accent, Space Grotesk- JetBrains Mono, per the mockups. (The ported Covaga dashboard screens use blue/Inter — that drift must be reconciled with the owner, not left mixed.)
- 7 LANGUAGES, ALWAYS (non-negotiable). EVERY user-facing surface — the landing,
the dashboard, every screen, label, message and empty state — must exist in ALL
seven locales: en, es, de, pt, ja, ko, zh-cn, with a language switcher. No
single-language screens. Wire i18n from the start (reuse the landing's
i18n/and the ported Covaga dashboard'sdicts.ts); a screen that is not fully translated is not done. - If no design exists for something new, ask the owner — do not ship generic UI.
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 · 77 lines · 1,032 tokens per session scan A cd4a7cf452aa
covaga.dev CLAUDE.md is an instructions file published in the GitHub repository covagashi/covaga.dev (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,032 tokens to every session, about $0.0052 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.
Other instructions, from other repositories
manga-trans AGENTS.md
AGENTS.md instructions for chiraitori/manga-trans, covering manga trans mcp — universal cli rules, required workflow, vision and non-vision models, content-preserving localization and batch completion contract.
manga-trans GEMINI.md
Gemini CLI instructions for chiraitori/manga-trans, covering manga trans project rules, mature fictional manga and required mcp workflow.
kagi-translate-mcp AGENTS.md
AGENTS.md instructions for subhangadirli/kagi-translate-mcp, a project described as: Model Context Protocol (MCP) server for Kagi Translate.
zendesk-mcp-server CLAUDE.md
Claude Code instructions for fruggr/zendesk-mcp-server, a project described as: Bring Zendesk deep into your AI assistant: find answers and draft, update and translate Help Center articles, and manage Support tickets end to end: comments, triage and attachments. All in plain language.
i18n-tools-mcp CLAUDE.md
Claude Code instructions for Trivle/i18n-tools-mcp, covering claude.md, project overview, commands, architecture and conventions.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.