agentmods.dev

lifeos-cli AGENTS.md

Repository instructions for coding agents working on the lifeos-cli project. They cover collaboration, writing conventions, validation, and safe software releases.

In plain words
What is it for?
Following the repository’s Git, issue, pull-request, text, language, validation, and release workflows.
Why use it?
They give an agent clear project rules so changes remain reviewable, compatible, and safe to release.

Instructions file for CodexOpenCode

11 5d ago A scan 1,011 tokens original Apache-2.0
View the source file lifeos-plus/lifeos-cli
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/lifeos-plus/lifeos-cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/lifeos-plus/lifeos-cli

Made for: Codex, OpenCode.

Per session 1,011 This file is loaded in full into every session.
When invoked 1,011 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 $0.01011 $0.01011
Opus 5 $0.00505 $0.00505
Sonnet 5 $0.00202 $0.00202
Haiku 4.5 $0.00101 $0.00101

Measured 2d ago against content hash 06d7c2be58b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lifeos-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 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 · 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

The following rules apply to coding agent collaboration in this repository. These complement the general CONTRIBUTING.md workflow.

1. Core Principles

  • Keep repository governance, release safety, and Python compatibility aligned.
  • Prefer small, traceable changes that preserve a releasable main branch.

2. Collaboration Workflow

  • Follow the Git, Issue, and PR workflow defined in CONTRIBUTING.md.
  • Create a new worktree based on the latest main for development work: first git fetch origin and fast-forward local main to origin/main, then create the worktree from main.
  • Use gh CLI for all issue and PR operations. Do not edit through the web UI.
  • Never use the Codex GitHub connector or any connector-backed GitHub mutation workflow. At any time, issue and PR operations must go through gh CLI only.
  • If GitHub permissions, authentication, policy, or environment constraints block a required gh operation, stop and ask the human collaborator to perform or authorize the needed step. Do not switch to the Codex GitHub connector as a fallback.
  • Create a tracking issue only for substantive development work that does not already have one, and link it in the PR description with Closes #xx or Related #xx. Trivial or mechanical changes — dependency bumps, CI/workflow tweaks, documentation fixes, small refactors, or other low-risk adjustments — do not require an issue; opening one for every small change adds noise. When in doubt, a PR alone is sufficient.
  • Keep issue and PR status synchronized when work scope changes.
  • Begin every issue and PR description with a TL;DR section that states the intent and expected outcome in plain language, so human readers can grasp the point at a glance before reading the full description.

3. Text and Language Conventions

  • Use Simplified Chinese for issue and PR descriptions, comments, and review notes; keep technical terms in English.
  • Always use English commit-message style for PR titles.
  • Use English for code, comments, commit messages, and canonical repository documents.
  • Localized Markdown companions are allowed when they are explicitly scoped, linked from the canonical English document, and kept aligned with it.
  • Keep the root README.md in English as the canonical repository entrypoint. Localized companions such as README.zh-Hans.md must link back to README.md, and README.md should link to the available localized companion documents.
  • Do not hard-wrap text in repository documents; keep each paragraph on a single line and let the editor soft-wrap long lines. Markdown tables, code blocks, and ASCII art are exempt because their line layout is meaningful.
  • For multi-line PR bodies or comments, write to a temporary file first and pass it through gh.

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.

  1. 2d ago First seen · 61 lines · 1,011 tokens per session scan A 06d7c2be58b9

Subscribe to this mod's changes

lifeos-cli AGENTS.md is an instructions file published in the GitHub repository lifeos-plus/lifeos-cli (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,011 tokens to every session, about $0.0051 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.

ai-agentsclilifeospostgresqlquantified-selftime-tracking
Related

Other instructions, from other repositories

supabase studio-composition-patterns.instructions.md

Instructions for supabase/supabase, covering react composition patterns review rules, core principle, when to flag, 1. boolean prop proliferation (high) and 2. render props instead of children (medium).

supabase/supabase · 592 tokens

supabase studio-shortcuts.instructions.md

Instructions for supabase/supabase, covering studio shortcut review rules, core principle, when to flag, preferred pattern and search inputs.

supabase/supabase · 698 tokens

supabase studio-e2e-tests.instructions.md

Instructions for supabase/supabase, covering studio e2e test review rules, selector priority (best to worst), patterns to flag and good practices to encourage.

supabase/supabase · 597 tokens

supabase studio-testing.instructions.md

Instructions for supabase/supabase, covering studio testing review rules, core principle, when to comment, which test type to suggest and reference.

supabase/supabase · 281 tokens

supabase studio-copy.instructions.md

Instructions for supabase/supabase, covering studio ui copy and agent checklist (not in the design doc).

supabase/supabase · 91 tokens

prest copilot-instructions.md

Instructions for prest/prest, covering copilot instructions for prest go backend, project scope, core engineering principles, solid principles for go and s — single responsibility.

prest/prest · 5,152 tokens