atc-claude-kanban: Instructions file for Claude Code

CLAUDE.md

atc-claude-kanban CLAUDE.md is an instructions file for Claude Code from atc-net/atc-claude-kanban. It costs 4,032 tokens per session, scanned A, original, MIT.

Repository instructions for a .NET command-line tool that displays Claude Code tasks, sessions, and subagents on a live Kanban board. A Kanban board is a visual list of work items grouped by their current status.

In plain words
What is it for?
Use them when developing, testing, running, or generating demo data for the Claude Code monitoring dashboard.
Why use it?
They explain how the dashboard watches Claude's local files, how to build and test it, and how to run it with different data folders or ports.

Instructions file for Claude Code

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

This is atc-net/atc-claude-kanban's own configuration. It tells Claude Code how to work on atc-claude-kanban itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything atc-claude-kanban configures →

Reuse

Borrowing it

Nothing to install: this file belongs to atc-net/atc-claude-kanban. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/atc-net/atc-claude-kanban/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/atc-net/atc-claude-kanban

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 atc-claude-kanban CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/atc-net/atc-claude-kanban/claude-md/github.svg)](https://agentmods.dev/instructions/atc-net/atc-claude-kanban/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/atc-net/atc-claude-kanban/claude-md"><img src="https://agentmods.dev/badge/instructions/atc-net/atc-claude-kanban/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for atc-claude-kanban CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/atc-net/atc-claude-kanban/claude-md"><img src="https://agentmods.dev/badge/instructions/atc-net/atc-claude-kanban/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,032 This file is loaded in full into every session.
When invoked 4,032 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.04032 $0.04032
Opus 5 $0.02016 $0.02016
Sonnet 5 $0.00806 $0.00806
Haiku 4.5 $0.00403 $0.00403

Measured 11d ago against content hash b5a6d6a12bc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

atc-claude-kanban 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 11d 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 · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 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.

Project Overview

A .NET 10 dotnet tool that serves a real-time Kanban dashboard for monitoring Claude Code agent tasks, sessions, and subagents. It watches ~/.claude/ directories, broadcasting changes via Server-Sent Events to a browser-based board.

Build & Test

# Build (Release mode enforces all analyzer rules as errors)
dotnet build -c Release

# Run tests (115 tests across 11 test classes)
dotnet test

# Run the dashboard locally
dotnet run --project src/Atc.Claude.Kanban -- --open

# Custom port
dotnet run --project src/Atc.Claude.Kanban -- --port 8080

# Point at a synthetic fixture instead of ~/.claude (used to regenerate README
# screenshots without real session data — see scripts/seed-demo-fixture.ps1)
dotnet run --project src/Atc.Claude.Kanban -- --dir <path>

Repository Structure

src/Atc.Claude.Kanban/
  Program.cs                    # Entry point, CLI args, auto-port discovery, WebApplication wiring
  CliOptions.cs                 # Parsed CLI argument record
  EndpointDefinitions/          # Atc.Rest.MinimalApi IEndpointDefinition implementations
    SessionEndpointDefinition   # /api/sessions, /api/sessions/{id}, /api/sessions/{id}/agents, /api/sessions/{id}/messages,
                                #   /api/sessions/{id}/messages/{uuid}/image/{blockIndex}, /api/sessions/{id}/tool-stats, /api/sessions/{id}/usage
    TaskEndpointDefinition      # /api/tasks/all, PUT/DELETE/POST task operations
    TeamEndpointDefinition      # /api/teams/{name}
    ProjectEndpointDefinition   # /api/projects
    PlanEndpointDefinition      # /api/plans/{slug}, /api/plans/{slug}/open
    SubagentEndpointDefinition  # /api/sessions/{id}/subagents, /api/sessions/{id}/subagents/{agentId}/messages
    SseEndpointDefinition       # /api/events (SSE), /api/version, /api/cache/clear
    UtilityEndpointDefinition   # /api/open-folder, /api/open-in-editor
  Contracts/
    Models/                     # ClaudeTask, SessionInfo, TeamConfig, SubagentInfo, MessageEntry, SessionTokenUsage,
                                #   AnswerPayload/AnswerQuestion/AnswerOption (AskUserQuestion), MessageImage, etc.
    Events/                     # SseNotification, FileChangeEvent
    Responses/                  # ErrorResult, UpdateResult, ToolStatsResponse/ToolStat, UsageResponse/UsageRow, etc.
    Parameters/                 # [AsParameters] records (SessionIdParameters, UserImageParameters, etc.)
  Helpers/
    PathHelper                  # Path traversal prevention (shared by TaskService, PlanService)
    TokenCostCalculator         # Model-aware token cost calculation (Opus/Sonnet/Haiku pricing)
  Extensions/                   # ServiceCollectionExtensions, WebApplicationExtensions
  Services/
    SessionService              # Session discovery from tasks/ + metadata from projects/, snapshots
    TaskService                 # Task CRUD, dependency validation, notes, snapshots
    TeamService                 # Team config reading with 5s cache TTL
    PlanService                 # Plan markdown reading
    SubagentService             # Subagent JSONL transcript parsing from projects/
    MessageService              # JSONL tail-reading for session/subagent conversation messages
    SessionActivityService      # Activity status (thinking/waiting/idle/error) + token usage (incl. latest-turn context size) from JSONL
    ToolStatsService            # Per-session tool-call aggregation (success/failed/rejected, output-impact) from JSONL
    UsageService                # Per-participant token/cost breakdown (lead session + each subagent), composes SessionActivityService + SubagentService
    ClaudeDirectoryWatcher      # BackgroundService with 4 FileSystemWatchers (extension-filtered)
    SseClientManager            # SSE client connection manager (singleton)
  UpdateCheck/
    Models/                     # NuGetVersionIndex, UpdateCheckCache (internal)
    Services/                   # UpdateCheckService (BackgroundService), logger messages
  wwwroot/
    index.html                  # Single-page Kanban + Timeline dashboard (embedded resource)
    images/icon.png             # ATC logo (favicon + sidebar)
  GlobalUsings.cs               # All using directives centralized here
test/Atc.Claude.Kanban.Tests/
  Helpers/                      # PathHelper, MockHttpMessageHandler
  Services/                     # SessionService, TaskService, TeamService, SubagentService,
                                # MessageService, SessionActivityService, PlanService,
                                # SseClientManager, UpdateCheckService, ToolStatsService, UsageService tests
scripts/
  seed-demo-fixture.ps1         # Materializes a synthetic ~/.claude tree for reproducible README screenshots (run with --dir)

Read the full file on GitHub · 165 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. 11d ago First seen · 165 lines · 4,032 tokens per session scan A b5a6d6a12bc3

Subscribe to this mod's changes

atc-claude-kanban CLAUDE.md is an instructions file published in the GitHub repository atc-net/atc-claude-kanban (10 stars, last pushed 1mo ago), licensed MIT. It adds 4,032 tokens to every session, about $0.0202 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.