What is Codemini-CLI AGENTS.md?

A set of instructions for working on Codemini CLI, a local coding assistant with a command-line interface, web interface, project indexing, skills, memory, and approval controls.

It helps assistants install dependencies, run tests and builds, start the CLI, and locate code for chat sessions, commands, project indexing, skills, and hooks.

It shows where key parts of the application live, reducing the risk of changing the wrong file or bypassing the intended task routing.

How havingautism/Codemini-CLI configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to havingautism/Codemini-CLI. 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/havingautism/Codemini-CLI/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/havingautism/Codemini-CLI

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/havingautism/codemini-cli/agents-md/github.svg)](https://agentmods.dev/instructions/havingautism/codemini-cli/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/havingautism/codemini-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/havingautism/codemini-cli/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/havingautism/codemini-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/havingautism/codemini-cli/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 909 This file is loaded in full into every session.

When invoked 909 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.

Model	Per session	Once invoked
Fable 5.1	$0.00909	$0.00909
Opus 5.5	$0.00364	$0.00364
Sonnet 5.5	$0.00182	$0.00182
Haiku 4.5	$0.00091	$0.00091

Measured 3d ago against content hash f62daaece10b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Codemini-CLI 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 3d 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 · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This repo is Codemini CLI, a local-first coding agent with a CLI, Web UI, project indexing, skills, memories, approvals, and Windows-first shell ergonomics.

Commands

Install dependencies: npm install
Run all tests: npm test
Build bundled Web UI: npm run build:web
Run CLI locally: npm start

Task Routing

CLI command dispatch: start in src/cli.js, then src/commands/.
Chat/session runtime behavior: start in src/core/chat-runtime.js.
Scheduled tasks: src/core/scheduled-task-store.js, src/core/scheduled-worker.js; see docs/agents/scheduled-tasks.md.
System prompt composition: start in src/core/system-prompt-composer.js and src/core/default-system-prompt.js.
Project map and file index behavior: start in src/core/project-index.js.
Skill discovery, routing, and rendering: start in src/core/command-loader.js, then src/core/skill-registry.js.
Skill hooks (Claude-compatible discover/run/session): start in src/core/skill-hooks-*.js, wired from src/core/chat-runtime.js and src/core/agent-loop.js.
Hook Profiles (custom/global/project plus skill-backed profiles): src/core/hook-profiles.js and src/core/project-hooks.js; Web UI entry under Skills in the sidebar.
Tool matcher aliases (Claude Bash→run etc.): src/core/skill-hooks-tool-aliases.js.
Reflect-to-skill behavior: start in src/core/reflect-skill.js.
Memory / Skill distillation decisions: src/core/harness/distillation.js, wired from memory-session-review.js and reflect-skill.js; see docs/agents/memory-skill-distillation.md.
Built-in tool behavior: start in src/core/tools.js.
Subagent delegation (run_subagent): start in src/core/chat-runtime.js (runSubAgentTask + onRunSubAgent), src/core/subagent-orchestrator.js, and src/core/subagent-handoff-store.js.
Fork branches (fork_task, same-state parallel branches sharing the parent prefix): fork-point capture in src/core/agent-loop.js, branch execution in src/core/chat-runtime.js (runForkTask + onForkTask).
Desktop shell and GitHub Release artifacts: desktop/main.cjs, desktop/electron-builder.config.cjs, .github/workflows/desktop-release.yml; see DESKTOP.md.
Web UI API routes: start in codemini-web/server.js.
Web UI state and chat behavior: start in codemini-web/client/src/context/app-context.jsx and relevant components under codemini-web/client/src/components/.

Read the full file on GitHub · 61 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.

3d ago Changed · +17 lines · +212 tokens per session f62daaece10b
2mo ago First seen · 44 lines · 697 tokens per session scan A d83233f02ffd

Subscribe to this mod's changes

Codemini-CLI AGENTS.md is an instructions file published in the GitHub repository havingautism/Codemini-CLI (31 stars, last pushed 2d ago), licensed MIT. It adds 909 tokens to every session, about $0.0036 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.

Building agents Memory and context WebUI ai-agents coding-agent coding-cli deepseek terminal-ai

Codemini-CLI AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Codemini-CLI AGENTS.mdhavingautism/Codemini-CLI	Instructions file	31	2d ago	MIT	A	909	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Codemini-CLI: Instructions file for Codex