agentmods.dev

palaia AGENTS.md

Development rules for palaia, a project containing Python and TypeScript code in one shared repository, called a monorepo. They cover branches, commits, tests, hooks, pull requests, and separate development tracks.

In plain words
What is it for?
Creating branches and commits, running the Python and TypeScript test suites, using the project's development server, and preparing changes for review.
Why use it?
They prevent unsafe changes such as pushing directly to the main branch, committing secrets, skipping checks, or mixing incompatible project versions.

Instructions file for CodexOpenCode

19 6d ago A scan 735 tokens original MIT
View the source file byte5ai/palaia
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/byte5ai/palaia/agents-md
Clone the repo
git clone --depth 1 https://github.com/byte5ai/palaia

Made for: Codex, OpenCode.

Per session 735 This file is loaded in full into every session.
When invoked 735 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 $0.00735 $0.00735
Opus 5 $0.00367 $0.00367
Sonnet 5 $0.00147 $0.00147
Haiku 4.5 $0.00073 $0.00073

Measured 2d ago against content hash 6e85dfd0edbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

palaia 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.

Agent Instructions

These rules apply to all AI agents working on this repository (Codex, Claude, Copilot, etc.).

Git Workflow

  • Never push directly to main. All changes go through feature branches and pull requests.
  • Branch naming: feat/, fix/, refactor/, docs/, chore/ prefixes.
  • Conventional commits: feat:, fix:, docs:, chore:, refactor:, test:, release:, dev:.
  • Never force-push to any shared branch.
  • Never commit secrets (.env, API keys, tokens, credentials).
  • Never skip hooks (--no-verify).

Pull Requests

  • Keep PR titles short (<70 chars), use conventional prefix.
  • One logical change per PR.
  • Ensure tests pass before requesting merge.

Project

  • Python + TypeScript monorepo: palaia/ (Python CLI/core) + packages/openclaw-plugin/ (TS plugin).
  • Tests: python3 -m pytest tests/ -q and cd packages/openclaw-plugin && npx vitest run.
  • Dev server runs on devhost (Tailscale) — never use localhost.

Pre-push Hook

A .hooks/pre-push hook blocks direct pushes to main/master. Override only when explicitly instructed:

ALLOW_PUSH_TO_MAIN=1 git push origin main

Two Development Tracks (v2 / v3)

This repository hosts two strictly separated lines of development:

  • v2 (stable, maintenance-only): the code at the repo root (palaia/, tests/, packages/openclaw-plugin/, docs/, skills/). Feature development is frozen. Only critical hotfixes (security, data loss, broken release) are made. Hotfix PRs target the v2-maintenance branch — never main. Release tags v2.x.y are cut from v2-maintenance.
  • v3 (active development): lives entirely under v3/ on main. Currently in the planning phase; code packages will be added under v3/ as they are created. v3/MASTERPLAN.md is the source of truth for v3 scope and roadmap. Significant v3 decisions are recorded in v3/decisions/ as ADRs.

v3 project conventions:

  • Repository language is English — code, comments, docs, ADRs, commit messages.
  • Every user-facing v3 feature must be checked against the standing design question "is an MCP App the right or a sensible surface for this?" — see v3/MASTERPLAN.md §4 (rule 8) and §5.7.

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 · 735 tokens per session scan A 6e85dfd0edbb

Subscribe to this mod's changes

palaia AGENTS.md is an instructions file published in the GitHub repository byte5ai/palaia (19 stars, last pushed 6d ago), licensed MIT. It adds 735 tokens to every session, about $0.0037 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-agentsembeddingsopenclawsemantic-searchsqlite
Related

Other instructions, from other repositories

mission-control CLAUDE.md

Claude Code instructions for builderz-labs/mission-control, covering mission control, prerequisites, setup, run and docker.

builderz-labs/mission-control · 891 tokens

obsidian-hybrid-search CLAUDE.md

Instructions for flowing-abyss/obsidian-hybrid-search, covering project guide for ai agents, quick reference, agent verification checklist, before your change and make your change, then run again.

flowing-abyss/obsidian-hybrid-search · 1,902 tokens

codemark GEMINI.md

Instructions for DanielCardonaRojas/codemark, covering development workflow and debugging with the tui logging system.

DanielCardonaRojas/codemark · 345 tokens

vecgrep CLAUDE.md

Instructions for jeffbai996/vecgrep, covering vecgrep — claude code working notes, what this is, architecture cheat sheet, design rules and don'ts.

jeffbai996/vecgrep · 1,439 tokens

openclaw-memory-vectorize AGENTS.md

Instructions for Atlas-Os1/openclaw-memory-vectorize, covering agents.md, quick setup (execute these commands), 1. install dependencies, 2. create vectorize index (skip if exists) and 3. deploy worker.

Atlas-Os1/openclaw-memory-vectorize · 1,081 tokens

ragfs CLAUDE.md

Instructions for Venere-Labs/ragfs, covering claude.md, build commands, testing, linting & formatting and running.

Venere-Labs/ragfs · 1,101 tokens