agentic-task-system AGENTS.md

A repository instruction file for Agentic Task System, an npm-workspaces monorepo: one project containing multiple related packages. ATS combines a task graph, a command-line interface, an MCP server, and adapters for task-management backends.

In plain words
What is it for?
Use it to locate core, CLI, MCP, and adapter code, inspect call graphs and architecture, find implementations across backends, and assess which packages may be affected by a change.
Why use it?
It gives coding agents a map of the packages and a way to inspect how code is connected before making changes. This helps identify affected adapters and avoids repeatedly searching the whole repository.

Instructions file for CodexOpenCode

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/renezander030/agentic-task-system/agents-md
Clone the repo
git clone --depth 1 https://github.com/renezander030/agentic-task-system

Made for: Codex, OpenCode.

Per session 437 This file is loaded in full into every session.
When invoked 437 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 $0.00437 $0.00437
Opus 5 $0.00218 $0.00218
Sonnet 5 $0.00087 $0.00087
Haiku 4.5 $0.00044 $0.00044

Measured 2d ago against content hash 9fa730db3ade, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-task-system AGENTS.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 2d 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.

AGENTS.md · 48 lines

What it actually says

AGENTS.md

Orientation for coding agents (Claude Code, Cursor, Claude Desktop, etc.) working on this repo. ATS is an npm-workspaces monorepo — an MCP server + CLI that turns your existing task manager into a governed task graph.

Layout

  • packages/core — the task model, adapter interface, retrieval, conformance.
  • packages/cli — the ats command surface.
  • packages/mcp — the MCP server.
  • packages/adapter-* — one per backend (ticktick, notion, github, obsidian, …); each implements the same interface (docs/adapter-interface.md).

Understand the code before you change it — use pi-codegraph

Don't re-grep the whole monorepo every session. pi-codegraph hands you a call-graph of the code as it is now:

pi-codegraph trust --repo . --label ats
pi-codegraph index --repo .
pi-codegraph arch -H                       # packages, routes, clusters
pi-codegraph search getTask                # every adapter's implementation, as a template
pi-codegraph trace loadAdapter --inbound   # where adapters get wired in
pi-codegraph impact                        # change core → which adapters break

Optional and external — nothing in the project depends on it. Full note in CONTRIBUTING.md.

Dev loop

npm install
npm run lint
npm test        # lint + unit (per-package proofs + publish-safety checks)

House rules

  • Writes are add-only — never drop a row or a link a human added.
  • No real or private data in examples — generic names only (writing, client-work, side-project).
  • A new adapter implements the 6 required methods in docs/adapter-interface.md and ships a test. pi-codegraph search getTask shows all existing ones as a template.
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. 2d ago First seen · 48 lines · 437 tokens per session scan A 9fa730db3ade

Subscribe to this mod's changes

agentic-task-system AGENTS.md is an instructions file published in the GitHub repository renezander030/agentic-task-system (11 stars, last pushed 2d ago), licensed MIT. It adds 437 tokens to every session, about $0.0022 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.