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/rdudov/task-agent/agents-mdgit clone --depth 1 https://github.com/rdudov/task-agentWhat 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 | $0.04469 | $0.04469 |
| Opus 5 | $0.02235 | $0.02235 |
| Sonnet 5 | $0.00894 | $0.00894 |
| Haiku 4.5 | $0.00447 | $0.00447 |
Grade A, and why
task-agent 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 yesterday.
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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Agent Project Rules
This repository contains a generic assistant workspace built around autonomous agent workflows.
Core Rule
Any substantial change to the agent engine must update documentation for both agents and humans in the same change.
Before implementation or architecture review, use this order: do nothing; remove or disable unnecessary behavior; configure or reuse the existing path; simplify the existing implementation; only then write the smallest necessary code. New code carries the burden of proof. A reviewer treats avoidable code or a more complex mechanism as a defect even when tests pass.
A substantial change includes:
- task lifecycle or task artifact structure
- skill discovery or skill execution rules
- agent orchestration behavior
- restore, resume, or publication conventions
If a change modifies one of these areas, update the relevant project docs before finishing the task.
Documentation Boundaries
AGENTS.mddefines project-wide operating rules.docs/explains repository architecture and workflows.- Each skill documents its own behavior in its own
SKILL.md.
Do not duplicate skill-specific instructions in project-level docs.
Agent entry points must not duplicate rules either. AGENTS.md is canonical for
project rules, .cursor/rules/*.mdc for always-on rules, and skills/ for
skills. CLAUDE.md only imports them and .claude/ only holds symlinks into
them. Edit the canonical file, never a .claude/ path, and add a CLAUDE.md
import line when a new Cursor rule is added. See
docs/claude-code-setup.md.
Task Conventions
Every substantial user task gets its own directory under tasks/ before substantive work begins. The default is to create a task; skipping is only appropriate when the request is clearly trivial or the user explicitly opts out of task artifacts.
A request is substantial when any of these apply:
- it has more than one meaningful step, such as research, implementation, verification, or documentation
- it creates or changes scripts, configuration, services, documentation, or durable artifacts
- it needs live checks against external systems, APIs, browsers, SSH, or other runtime services
- it performs work in another repository or absolute path outside this workspace
- it is a follow-up that continues the same non-trivial goal
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.
- yesterday First seen · 227 lines · 4,469 tokens per session scan A 1c8312e02138
task-agent AGENTS.md is an instructions file published in the GitHub repository rdudov/task-agent (4 stars, last pushed 2d ago), licensed MIT. It adds 4,469 tokens to every session, about $0.0223 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.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.