What is task-cli GEMINI.md?

A guide for building software with large-language-model agents, where people define the system and the agents implement it. It describes a workflow covering requirements, design, data, utilities and implementation.

Use it to plan and build LLM-based projects, decide what humans and agents should handle, and organize project files and core abstractions.

It gives human and AI collaborators clearer responsibilities and encourages small solutions, written designs and regular feedback.

task-cli GEMINI.md — Instructions file by sunjiawe

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/sunjiawe/task-cli/gemini-md

Clone the repo

git clone --depth 1 https://github.com/sunjiawe/task-cli

Made for: Gemini CLI.

Per session 13,771 This file is loaded in full into every session.

When invoked 13,771 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.

Model	Per session	Once invoked
Fable 5	$0.13771	$0.13771
Opus 5	$0.06885	$0.06885
Sonnet 5	$0.02754	$0.02754
Haiku 4.5	$0.01377	$0.01377

Measured yesterday against content hash 272ad8abf3cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-cli GEMINI.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.

GEMINI.md · 1,669 lines

How it starts

The opening of the file, as written. The whole thing — 1,669 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Coding: Humans Design, Agents code!

If you are an AI agent involved in building LLM Systems, read this guide VERY, VERY carefully! This is the most important chapter in the entire document. Throughout development, you should always (1) start with a small and simple solution, (2) design at a high level (docs/design.md) before implementation, and (3) frequently ask humans for feedback and clarification. {: .warning }

Agentic Coding Steps

Agentic Coding should be a collaboration between Human System Design and Agent Implementation:

Steps	Human	AI	Comment
1. Requirements	★★★ High	★☆☆ Low	Humans understand the requirements and context.
2. Flow	★★☆ Medium	★★☆ Medium	Humans specify the high-level design, and the AI fills in the details.
3. Utilities	★★☆ Medium	★★☆ Medium	Humans provide available external APIs and integrations, and the AI helps with implementation.
4. Data	★☆☆ Low	★★★ High	AI designs the data schema, and humans verify.
5. Node	★☆☆ Low	★★★ High	The AI helps design the node based on the flow.
6. Implementation	★☆☆ Low	★★★ High	The AI implements the flow based on the design.
7. Optimization	★★☆ Medium	★★☆ Medium	Humans evaluate the results, and the AI helps optimize.
8. Reliability	★☆☆ Low	★★★ High	The AI writes test cases and addresses corner cases.

Requirements: Clarify the requirements for your project, and evaluate whether an AI system is a good fit.
- Understand AI systems' strengths and limitations:
  - Good for: Routine tasks requiring common sense (filling forms, replying to emails)
  - Good for: Creative tasks with well-defined inputs (building slides, writing SQL)
  - Not good for: Ambiguous problems requiring complex decision-making (business strategy, startup planning)
- Keep It User-Centric: Explain the "problem" from the user's perspective rather than just listing features.
- Balance complexity vs. impact: Aim to deliver the highest value features with minimal complexity early.

Read the full file on GitHub · 1,669 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.

yesterday First seen · 1,669 lines · 13,771 tokens per session scan A 272ad8abf3cc

Subscribe to this mod's changes

task-cli GEMINI.md is an instructions file published in the GitHub repository sunjiawe/task-cli (2 stars, last pushed 1y ago), licensed Apache-2.0. It adds 13,771 tokens to every session, about $0.0689 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.

Data and AI Planning Project Management Project management ai ai-agents cli gantt-chart gemini-cli

task-cli GEMINI.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Agentic Coding: Humans Design, Agents code!

Agentic Coding Steps

What this file has done since we first saw it

Other instructions, from other repositories

gantt AGENTS.md

single-file-wbs CLAUDE.md

operator CLAUDE.md

FlowBoard AGENTS.md

STAR AGENTS.md

AllBeads CLAUDE.md