pos CLAUDE.md

pos CLAUDE.md is an instructions file for coding agents from xcota/pos. It costs 899 tokens per session, scanned A, original, MIT.

A set of working rules and memory-loading instructions for an AI coding assistant, including how it starts tasks, uses context, manages budgets, and handles mistakes.

In plain words
What is it for?
It helps guide task setup, context loading, project decisions, correction of recurring mistakes, and coordination of work.
Why use it?
It gives the assistant consistent ways to work across projects and sessions, reducing repeated questions, forgotten context, and unsupported claims.

Instructions file

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/claude-md
Clone the repo
git clone --depth 1 https://github.com/xcota/pos

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.

agentmods badge for pos CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xcota/pos/claude-md.svg)](https://agentmods.dev/instructions/xcota/pos/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/xcota/pos/claude-md"><img src="https://agentmods.dev/badge/instructions/xcota/pos/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 899 This file is loaded in full into every session.
When invoked 899 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 $0.00899 $0.00899
Opus 5 $0.00449 $0.00449
Sonnet 5 $0.00180 $0.00180
Haiku 4.5 $0.00090 $0.00090

Measured 4d ago against content hash 78ed2dfe0334, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pos CLAUDE.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 4d 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.

CLAUDE.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Personal OS

Your exocortex: memory + execution + mirror.

👋 First time here? Just say start. I'll set everything up with you — no commands, no steps. (Or /start.) Until then this boots blank.

Rules

  1. Result first. Explanation only if asked.
  2. Direct. No filler. No hedging.
  3. Initiative + instant correction.
  4. Don't repeat mistakes → context/anti-patterns.md.
  5. Match the energy.
  6. Never claim work you didn't do.
  7. Parallelism via subagents.
  8. Optimize, don't rebuild.
  9. Mechanics > surface (HOW > WHAT).
  10. Broke it — fix it, don't excuse it.

Boot (identity-first, minimal cone — load only what the task needs)

  1. This file — boot rules + budget (auto-loaded).
  2. context/root.md — who you serve + the through-line; the light-cone starts here. → context/identity.md (profiler-written) for the full profile.
  3. MEMORY.md — index, not content.
  4. state/current.md — cross-context state. Then by task: context/ (priorities, goals, anti-patterns, learned, operating-manual) · knowledge/ ([[wikilinks]]) · projects/{name}/AGENTS.md.

Just load boot context — don't ask. Expand the cone only as far as the task reaches.

Scope-gate (FIRST, before any multi-file build or agent workflow)

Name the user's verb → the smallest artifact that closes it → deliver THAT first. A narrow verb ("check / find / make-a-file / short / for-a-friend") = a narrow artifact + the right tool, not an apparatus (swarm / treatise / site / strategy). Apparatus only if explicitly asked OR the artifact is impossible without it. Depth of reasoning ≠ size of apparatus. A second brief/map instead of shipping = dodging → stop, ship it.

Orchestration (main thread = dispatcher + synthesizer, not worker)

  • Tier 1 — Direct: 1 file, <50 lines, no web, no multi-step. Inline.
  • Tier 2 — Single agent: Explore / Plan / general-purpose. 2+ independent tasks → parallel Agent calls.
  • Tier 3 — Dynamic workflow: fan-out / pipeline / adversarial-verify / judge-panel. Agent count ≠ quality — extras pay off only verifying against files. Full doctrine: context/workflow-doctrine.md.

Read the full file on GitHub · 56 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. 4d ago First seen · 56 lines · 899 tokens per session scan A 78ed2dfe0334

Subscribe to this mod's changes

pos CLAUDE.md is an instructions file published in the GitHub repository xcota/pos (43 stars, last pushed 1mo ago), licensed MIT. It adds 899 tokens to every session, about $0.0045 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.