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/keshrath/agent-tasks/claude-mdgit clone --depth 1 https://github.com/keshrath/agent-tasksWrote 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/keshrath/agent-tasks/claude-md)<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="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 | $0.01319 | $0.01319 |
| Opus 5 | $0.00660 | $0.00660 |
| Sonnet 5 | $0.00264 | $0.00264 |
| Haiku 4.5 | $0.00132 | $0.00132 |
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 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 — 103 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/
domain/ tasks (stages, dependencies, artifacts, claiming), events, validation
storage/ SQLite (better-sqlite3, WAL mode)
transport/ REST (node:http), WebSocket (ws), MCP (stdio)
ui/ Vanilla JS kanban dashboard (no build step for UI)
- No frameworks — no React, Vue, Express. Pure Node.js + TypeScript.
context.tsis the DI root — wires all services together.- UI files (
index.html,app.js,styles.css) are plain files copied todist/ui/on build. - Soft deps:
AgentBridge→ agent-comm (notifications),KnowledgeBridge→ agent-knowledge (push learnings/decisions on task completion). Both HTTP-only, fail-open.
UI / Dashboard
- Layout: Kanban board with columns per pipeline stage
- Icons: Material Symbols Outlined (via Google Fonts CSS). No emojis.
- Fonts: Inter (UI text), JetBrains Mono (code/data)
- Theme: Light/dark toggle via
data-theme="dark"attribute on<html> - Design tokens: CSS custom properties (
--bg,--accent,--border,--shadow-*, etc.) - Accent color:
#5d8da8 - Radii: 8px cards/columns, 4px tags
- Column headers: Uppercase, 12px, weight 600, letter-spacing 0.5px
- Tags: Color-coded by type (project=accent, assignee=purple, priority=orange, artifacts=blue, blocked=red)
Code Style
- No inline comments — only file-level section headers (
// === ... ===or// --- ... ---) - No Co-Authored-By or Claude branding in commits
- ESLint + Prettier enforced via lint-staged (husky pre-commit)
Versioning
- Version lives in
package.jsonand is read at runtime (REST/health, WS state payload, UI header) - Never hardcode version strings
- Every commit must bump the patch version minimum
- Commit message format:
v1.0.x: short description
Build & Test
npm run build # tsc + copy UI files to dist/
npm test # vitest (unit + integration)
npm run check # typecheck + lint + format + test
npm run dev # watch mode (tsc + nodemon)
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 · 103 lines · 1,319 tokens per session scan A 41057ef18653
agent-tasks CLAUDE.md is an instructions file published in the GitHub repository keshrath/agent-tasks (15 stars, last pushed 4mo ago), licensed MIT. It adds 1,319 tokens to every session, about $0.0066 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
session-collab-mcp AGENTS.md
AGENTS.md instructions for leaf76/session-collab-mcp, covering agents.md - session collab mcp, structure, where to look, commands and single test.
session-collab-mcp CLAUDE.md
Claude Code instructions for leaf76/session-collab-mcp, covering session collab mcp, what it does, installation, option 1: claude code plugin (recommended) and add marketplace.
laver-mcp AGENTS.md
AGENTS.md instructions for Developyn/laver-mcp, covering agents.md — @laver/mcp, development and git rules.
Kanera CLAUDE.md
Claude Code instructions for happendev/Kanera, covering purpose, repo shape, commands, backend rules and schema workflow.
Kanera AGENTS.md
AGENTS.md instructions for happendev/Kanera, a project described as: A polished project management tool with workspace-wide lists, labels and custom fields, automations, assigned work, realtime collaboration, REST API and MCP support.
clink-mcp-server CLAUDE.md
Instructions for Voxos-ai-Inc/clink-mcp-server, covering clink mcp server - development guide, source location, publishing to github, first-time setup (already done) and add the github remote.