agentmods.dev

c9s CLAUDE.md

c9s CLAUDE.md is an instructions file for Claude Code from StefanoGuerrini/c9s. It costs 2,256 tokens per session, scanned A, original, MIT.

A terminal dashboard for Claude Code that shows your projects and coding sessions in one place. It reads local Claude Code files and lets you create or attach to sessions through tmux, a tool for managing terminal windows.

In plain words
What is it for?
Use it to browse Claude Code projects, view session details and token usage, start new sessions, and reconnect to running ones.
Why use it?
It removes the need to search through folders or remember which terminal contains a session. It also works without setting up a server or connecting to an API.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

not rated 5 29d ago A scan 2,256 tokens original MIT
View the source file StefanoGuerrini/c9s stefanoguerrini.dev
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/stefanoguerrini/c9s/claude-md
Clone the repo
git clone --depth 1 https://github.com/StefanoGuerrini/c9s

Made for: Claude Code.

Wrote 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.

agentmods badge for c9s CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/stefanoguerrini/c9s/claude-md.svg)](https://agentmods.dev/instructions/stefanoguerrini/c9s/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/stefanoguerrini/c9s/claude-md"><img src="https://agentmods.dev/badge/instructions/stefanoguerrini/c9s/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,256 This file is loaded in full into every session.
When invoked 2,256 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original 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 5.1 $0.02256 $0.02256
Opus 5 $0.01128 $0.01128
Sonnet 5 $0.00451 $0.00451
Haiku 4.5 $0.00226 $0.00226

Measured 6d ago against content hash ea17fcb0a5dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

c9s 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 6d 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.

CLAUDE.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

c9s — Claude Code Dashboard

A simple terminal dashboard for Claude Code. Run c9s, see all your projects and sessions, create new ones, attach to running ones. Zero setup — it reads directly from ~/.claude/.

Inspired by k9s: simple, fast, keyboard-driven.

Vision

  • Dashboard-first: Launch c9s → see all your Claude Code projects and sessions across all directories
  • Zero setup: Discovers existing sessions from ~/.claude/history.jsonl and ~/.claude/projects/
  • tmux for sessions: Real interactive Claude Code terminals via tmux windows (no in-process terminal emulator)
  • Simple: One binary + tmux. No daemon, no plugins, no agent mail. Just a dashboard.
  • Future: Extend to other CLI agents (Codex, Gemini) — but Claude Code first.

Data sources (all local, no API)

What Where
All sessions + projects ~/.claude/history.jsonl
Token usage per session ~/.claude/projects/<path>/<session>.jsonl → sum message.usage
Session name/title sessions-index.json → customTitle, or history.jsonl → display
Session status JSONL file mtime + ps/lsof process detection

Testing

Always write tests for every change. No code lands without corresponding test coverage.

  • Tests live next to the code they test (foo_test.go alongside foo.go)
  • Run all tests: go test ./... -count=1
  • Run a specific package: go test ./internal/claude/ -v
  • Use t.TempDir() for any file I/O in tests — never write to real paths
  • Table-driven tests preferred for functions with multiple input/output cases
  • Test both happy paths and edge cases (missing files, empty inputs, etc.)

Architecture

c9s/
├── main.go                          # Bubbletea TUI + tmux bootstrap + keybindings
├── internal/
│   ├── claude/
│   │   ├── sessions.go              # Session discovery, token reading, process detection
│   │   └── sessions_test.go         # Tests
│   ├── config/
│   │   ├── config.go                # Config loading from ~/.c9s/config.json
│   │   └── config_test.go           # Tests
│   ├── git/
│   │   ├── worktree.go              # Git worktree discovery + creation
│   │   └── worktree_test.go         # Tests
│   └── tmux/
│       ├── tmux.go                  # tmux CLI wrapper, pane status, status bar
│       ├── tmux_test.go             # Tests
│       ├── exec_unix.go             # syscall.Exec (Unix)
│       └── exec_windows.go          # Stub (Windows)

Read the full file on GitHub · 183 lines

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. 6d ago First seen · 183 lines · 2,256 tokens per session scan A ea17fcb0a5dc

Subscribe to this mod's changes

c9s CLAUDE.md is an instructions file published in the GitHub repository StefanoGuerrini/c9s (5 stars, last pushed 29d ago), licensed MIT. It adds 2,256 tokens to every session, about $0.0113 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.

Building agentsaibubbleteaclaude-codeclidashboarddeveloper-tools
Related

Other instructions, from other repositories

Vibe-Research AGENTS.md

AGENTS.md instructions for simonlin1212/Vibe-Research, covering vibe-research-agent 金融研究宪法, 0. 三条不可越线, 1. 数据纪律(五问 gate:给出任何数字或结论前逐条自问), 2. 研究哲学(评估框架,不是预测工具) and 3. 估值口径(你只选输入、解释输出;计算交给 calc/).

simonlin1212/Vibe-Research · 4,469 tokens

worldmonitor AGENTS.md

AGENTS.md instructions for koala73/worldmonitor, covering agents.md, own the outcome, start safely, find the code and its checks and critical boundaries.

koala73/worldmonitor · 1,425 tokens

vizro copilot-instructions.md

Copilot instructions for mckinsey/vizro, covering github copilot instructions for vizro, pull requests from bots and automated tooling and everything else.

mckinsey/vizro · 332 tokens

openclaw-dashboard CLAUDE.md

Claude Code instructions for mudrii/openclaw-dashboard, covering go development standards, project constraints, internal packages, environment and commands.

mudrii/openclaw-dashboard · 1,519 tokens

metabase copilot-instructions.md

Copilot instructions for metabase/metabase, covering metabase developer assistant instructions, code review standards, security critical issues, performance red flags and code quality essentials.

metabase/metabase · 377 tokens

neko-master copilot-instructions.md

Instructions for foru17/neko-master: All repo guidance lives in AGENTS.md — commands, code conventions, key contracts, and the project map. Follow it.

foru17/neko-master · 118 tokens