agent-tasks: Instructions file for Claude Code

CLAUDE.md

agent-tasks CLAUDE.md is an instructions file for Claude Code from keshrath/agent-tasks. It costs 2,695 tokens per session, scanned A, original, MIT.

Project instructions for agent-tasks, a TypeScript task-management system with a REST API, WebSocket support, MCP access, and a kanban dashboard.

In plain words
What is it for?
Use them when changing the task domain, SQLite storage, API or MCP transport, WebSocket features, or the plain JavaScript dashboard.
Why use it?
They give agents the project's architecture, dependency-injection rules, interface conventions, and build expectations.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions .claude-plugin; mentions Claude Code.

This is keshrath/agent-tasks's own configuration. It tells Claude Code how to work on agent-tasks 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 agent-tasks configures →

Reuse

Borrowing it

Nothing to install: this file belongs to keshrath/agent-tasks. 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/keshrath/agent-tasks/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/keshrath/agent-tasks

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 agent-tasks CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/keshrath/agent-tasks/claude-md/github.svg)](https://agentmods.dev/instructions/keshrath/agent-tasks/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/keshrath/agent-tasks/claude-md"><img src="https://agentmods.dev/badge/instructions/keshrath/agent-tasks/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 agent-tasks CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/keshrath/agent-tasks/claude-md"><img src="https://agentmods.dev/badge/instructions/keshrath/agent-tasks/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,695 This file is loaded in full into every session.
When invoked 2,695 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 $0.02695 $0.02695
Opus 5.5 $0.01078 $0.01078
Sonnet 5.5 $0.00539 $0.00539
Haiku 4.5 $0.00269 $0.00269

Measured 4d ago against content hash 16b9f8aea7f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-tasks 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.

CLAUDE.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-tasks

Architecture

Layered architecture with explicit dependency injection (no global state):

src/
  index.ts    MCP stdio entry point; one process serves the REST API (leader election on the port; the others retry and take over)
  server.ts   REST server (standalone: node dist/server.js [--port] [--db])
  domain/     tasks (stages, dependencies, artifacts, claiming), events, validation
  storage/    SQLite (better-sqlite3, WAL mode)
  transport/  REST (node:http, JSON only) + guard.ts (Host/Origin/Content-Type), MCP (official SDK `Server` over stdio, mcp.ts)
plugin/       Claude Code plugin (.mcp.json + one mod: hooks/register.tsx + view.tsx = /pipeline pane)
  • No frameworks — no React, Vue, Express. Pure Node.js + TypeScript; runtime deps are the official MCP SDK (@modelcontextprotocol/server) and better-sqlite3. No agent-common.
  • context.ts is the DI root — wires all services together.
  • src/ stays host-agnostic; Claude-specific glue belongs in plugin/ (the mod) or scripts/hooks/ (command hooks wired by scripts/setup.js).
  • Soft deps: AgentBridge → agent-comm (notifications), KnowledgeBridge → agent-knowledge (push learnings/decisions on task completion). Both HTTP-only, fail-open.

UI surfaces

There is no web dashboard (removed in 2.0, with the WebSocket, the UI files and the agent-desk plugin).

  • Claude Code pane (plugin/hooks/register.tsx + view.tsx, Claude Code 2.1.289+ function hooks): /pipeline opens it (the built-in /tasks is taken); /pipeline 12 opens task 12, /pipeline <text> filters the board. Tabs Board (open tasks by stage, Find over id, title, agent, project and tags, waits for #N on blocked rows), Done (recently closed, who and where, the result beneath), New (title, project, priority, tags, description; Enter walks the fields). Task detail: stage strip, actions for a task in progress (Advance › next, Complete, ‹ Send back with a stage, Fail; Cancel, Delete with a confirmation), facts, description, subtasks, artifacts (unfold as Markdown), comments + a comment field. No Claim: agents claim with task_stage, and an assignee that is no live agent-comm agent gets reaped by the cleanup; an unclaimed task has no Advance either (it would sit in progress with nobody on it). A blocked task shows no Advance or Complete (the domain refuses both while a blocks dependency is open), only what it waits for. A stage gate is said under the actions from task_get's gate_needs (TaskService.gateNeeds, the gate's one reader; checkStageGate refuses Advance and Complete on it), said with who gives it (gateHint); Advance and Complete lose primary while it holds. The ring never lands in a text field when /pipeline opens or moves to a view (a later /pipeline N would be typed into it and posted): a comment gate sends it to the comment field only after a press the gate refused (toCommentIfGated, which also shortens that refusal to ✗ #N can't leave <stage> yet since the hint says why, and keeps a refused Complete's form open with its words and the hint under it); the New tab is the one view that starts in a field. A stage nobody works on folds past 10 rows (boardGroups; board folds survive opening a task); unfolded, its toggle stays after row 10 and the ring goes to the first row it showed. Status line entry and the board's summary are the same text (headline() in view.tsx); toasts only for tasks that finished or reached review since the last poll; one prompt.context block with what is in flight. Acts as AGENT_TASKS_USER, else the OS user (created_by, comment author, by). Polls GET /api/board every 5 s while open, 30 s while closed. REST only, through $.http.fetch on AGENT_TASKS_PORT (default 3422). View state in $.state (contract plugin/types/index.d.ts). Opened as a plain sidebar (no closeOnEscape); /pipeline reports isPlaced: false with the reason. Focus lands explicitly after every navigation and action, a fold's toggle included (landing(), toggle() in register.tsx): the engine keeps the ring at its place in the focus order across a redraw, not on a key, so a redraw that adds or drops a control above it would move it; a key that names the new state (foldKey, advance:<stage>, complete:<stage> from completeKey, the fresh comment:<rev>, Refresh's refresh:<rev> from refreshKey) makes the focus wait for the drawing that shows it; landOnNewBoard waits on Refresh, a button, so nothing typed meanwhile lands in a field. Back up after the server was away, the ring returns where it was before (landBack), else lands as on a fresh open. The pane's own moves and its autoFocus taking the ring both reach ui.focus as origin plugin; focusOn marks its own (ownMoves, a set: moves overlap), so a take (ctrl+x tab) is put back on the last focused key while it is drawn, and openPane clears focused so a command's view starts at its landing. The element landing() names is also drawn autoFocus, and /pipeline closes and reopens an open pane after setting the view, because a take would otherwise put the ring back on the element it last held. Every function that takes $ must be a top-level declaration (claude plugin validate enforces it). Tests: plugin/tests/*.test.ts under claude plugin test plugin (npm run plugin:check); vitest excludes plugin/. Type-check with a tsconfig outside the folder (never tsc -p plugin, it emits .js into plugin/).
  • MCP tool results (JSON + the pipeline footer) for every other host.

Read the full file on GitHub · 102 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. 4d ago Changed · +1 lines · +532 tokens per session 16b9f8aea7f8
  2. 5d ago Changed · -2 lines · +844 tokens per session 14e0fb1c1b6e
  3. 1mo ago First seen · 103 lines · 1,319 tokens per session scan A 41057ef18653

Subscribe to this mod's changes

agent-tasks CLAUDE.md is an instructions file published in the GitHub repository keshrath/agent-tasks (22 stars, last pushed 5d ago), licensed MIT. It adds 2,695 tokens to every session, about $0.0108 per session on Opus 5.5. 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens