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/resetnak/cooldeck/claude-mdgit clone --depth 1 https://github.com/Resetnak/cooldeckWrote 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/resetnak/cooldeck/claude-md)<a href="https://agentmods.dev/instructions/resetnak/cooldeck/claude-md"><img src="https://agentmods.dev/badge/instructions/resetnak/cooldeck/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 | $0.01426 | $0.01426 |
| Opus 5 | $0.00713 | $0.00713 |
| Sonnet 5 | $0.00285 | $0.00285 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
cooldeck 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 4d 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 — 113 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.
What this is
CoolDeck - a keyboard-first terminal dashboard (Bubble Tea / Charm v2) for Coolify.
Single Go module, github.com/resetnak/cooldeck, Go 1.26.6+, no CGO.
Commands
make check # fmt-check + vet + lint + test + build - run before every PR
make build # -> bin/cooldeck, injects version/commit/date ldflags
make run # go run ./cmd/cooldeck --demo
make test-race
make test-update-golden # UPDATE_GOLDEN=1 go test ./... - refresh TUI snapshots
make lint # staticcheck + golangci-lint, pinned to the CI versions
make bench # benchmarks in internal/tui/views
make vuln # govulncheck
Single test / single case:
go test ./internal/tui/ -run TestGoldenViews/dashboard-wide -v
go test ./internal/coolify/ -run TestSplitDeployments
go test ./internal/tui/ -run TestGoldenViews -update # -update flag == UPDATE_GOLDEN=1
CI additionally runs golangci-lint (config .golangci.yml, v2 schema, curated linter set) on Linux
and the full test matrix on ubuntu/macos/windows. -race is skipped on Windows.
Architecture
Layered so the same use cases back the TUI, the MCP server, and any future CLI subcommand:
cmd/cooldeck → internal/cli (cobra, flags, config load, service construction)
→ internal/tui (Bubble Tea model + views; presentation only)
→ internal/mcpserver (MCP tools over stdio; `cooldeck mcp`)
→ internal/app (Service interface = the use cases)
├── internal/app/demo deterministic fake Service
└── internal/coolify HTTP client + DTO → domain mapping
→ internal/domain, config, credentials, logging, platform, version
docs/architecture.md has the full picture; docs/decisions/ holds seven ADRs (Go+Charm v2,
direct REST instead of MCP, domain/DTO split, credential storage, responsive layout, MCP server,
fleet-tail concurrency).
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.
- 4d ago First seen · 113 lines · 1,426 tokens per session scan A 08dbfa9adc02
cooldeck CLAUDE.md is an instructions file published in the GitHub repository Resetnak/cooldeck (23 stars, last pushed 2d ago), licensed MIT. It adds 1,426 tokens to every session, about $0.0071 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
tuitube AGENTS.md
Instructions for gitcoder89431/tuitube, covering agents.md, project intent, checklist for adding a new feature, key packages and logging.
bagent AGENTS.md
AGENTS.md instructions for damienp199/bagent, covering bagent — consignes pour agents, plateforme, installer (méthode unique recommandée), pièges — à respecter impérativement and vérifier l'installation.
CodeWhale CLAUDE.md
Claude Code instructions for Hmbown/CodeWhale, a project described as: Open-source coding agent for your terminal, built in Rust and on a journey of continuous community improvement. Issues and PRs welcome.
opentui AGENTS.md
AGENTS.md instructions for anomalyco/opentui, covering opentui agent guide, engineering, tooling and runtimes, verification and portable ffi.
tuicr AGENTS.md
AGENTS.md instructions for agavra/tuicr, covering agents.md - tuicr, project structure, key types, data flow and important implementation details.
cs CLAUDE.md
Claude Code instructions for boyter/cs, covering claude.md, project overview, build & test commands, architecture and query pipeline (pkg/search/).