agentmods.dev

pos AGENTS.md

Workspace startup instructions for an agent-managed personal knowledge system. They specify which identity, memory, daily-note, project, and operating-rule files to read before starting work.

In plain words
What is it for?
They are for initializing a work session, loading current and long-term context, and checking whether the workspace has been personalized.
Why use it?
They give the agent the context needed to follow the workspace’s conventions and remember relevant personal or project information.

Instructions file for CodexOpenCode

43 1mo ago A scan 629 tokens original MIT
View the source file xcota/pos
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/xcota/pos/agents-md
Clone the repo
git clone --depth 1 https://github.com/xcota/pos

Made for: Codex, OpenCode.

Per session 629 This file is loaded in full into every session.
When invoked 629 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 $0.00629 $0.00629
Opus 5 $0.00315 $0.00315
Sonnet 5 $0.00126 $0.00126
Haiku 4.5 $0.00063 $0.00063

Measured 2d ago against content hash 620b625c92b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pos 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 · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Workspace Boot Rules

This folder is home. Treat it as the canonical Personal OS workspace. (Boot file for Codex / non–Claude-Code agents; Claude Code reads CLAUDE.md.)

Session Boot

Before doing task work:

  1. Read CLAUDE.md (operating rules + orchestration).
  2. Read context/identity.md — your profile. If it still contains {{ }} placeholders or an empty profile_version:, the vault is not personalized yet: read .claude/skills/start/SKILL.md and run it — start is the entry point that sets everything up (it orchestrates /svoboda-profiler + /vault-scaffolder for you). Tell the user they only need to say start.
  3. Read daily/YYYY-MM-DD.md for today and yesterday.
  4. In a main/direct session, read MEMORY.md.
  5. For project work, read projects/{project}/AGENTS.md and/or projects/{project}/context.md if present.

Don't ask permission for this boot context. Just load it.

Memory

  • Daily notes: daily/YYYY-MM-DD.md — chronological source of recent state.
  • Long-term index: MEMORY.md — loaded in direct/main sessions, not shared/group contexts.
  • Durable lessons: context/learned.md.
  • Mistakes to avoid: context/anti-patterns.md.
  • Current cross-context state: state/current.md.
  • Significant decisions: state/decisions/.

Write down decisions, durable context, corrections, and lessons. "Mental notes" do not survive session restarts.

Safety

  • Do not exfiltrate private data.
  • Do not send emails, posts, or external messages without explicit user intent.
  • Do not run destructive commands without asking.
  • Prefer recoverable operations; trash beats permanent delete.
  • Preserve user changes. Never revert unrelated dirty worktree files.

Language

Always respond in the language of the most recent user message. Language mismatch breaks trust.

Tools And Skills

  • Skills live under .claude/skills/. If a skill is invoked or clearly applies, read its SKILL.md.
  • Optional modules ship under modules/ — flip enabled: true in modules.yaml, then run /enable-modules to activate one (it creates dirs and seeds routes).
  • For browser/local UI work, prefer configured browser/computer-use tools over ad hoc shell shortcuts.
  • For repo edits, keep changes scoped and commit meaningful work.

Read the full file on GitHub · 48 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 · 48 lines · 629 tokens per session scan A 620b625c92b4

Subscribe to this mod's changes

pos AGENTS.md is an instructions file published in the GitHub repository xcota/pos (43 stars, last pushed 1mo ago), licensed MIT. It adds 629 tokens to every session, about $0.0031 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.

Data and AIMemory and contextagent-memoryai-agentsai-memoryclaude-codeexocortexknowledge-graph
Related

Other instructions, from other repositories

vellis AGENTS.md

Instructions for volantlabs/vellis, covering agents.md, repository purpose, startup checks, installing vellis for a user and model-first component workflow.

volantlabs/vellis · 4,953 tokens

dakera-cli CLAUDE.md

Instructions for Dakera-AI/dakera-cli, covering dakera-cli, key commands, architecture and conventions.

Dakera-AI/dakera-cli · 282 tokens

cli AGENTS.md

Instructions for konteks/cli, covering agent instructions, project overview, tech stack, repository layout and common commands.

konteks/cli · 1,050 tokens

context-canopy AGENTS.md

Instructions for YusenZhang0601/context-canopy, covering contextcanopy agent entry, route before acting, privacy and authority boundary, portability claims and completion evidence.

YusenZhang0601/context-canopy · 586 tokens

context-canopy CLAUDE.md

Instructions for YusenZhang0601/context-canopy, a project described as: Portable, local-first AI agent memory and personal context—switch agents without losing identity, goals, rules, or evidence.

YusenZhang0601/context-canopy · 46 tokens

dakera-go CLAUDE.md

Claude Code instructions for Dakera-AI/dakera-go, covering dakera-go, key commands, architecture and conventions.

Dakera-AI/dakera-go · 267 tokens