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.
npx agentmods add instructions/aisystant/pack-personal/claude-mdgit clone --depth 1 https://github.com/aisystant/PACK-personalWrote 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.
[](https://agentmods.dev/instructions/aisystant/pack-personal/claude-md)<a href="https://agentmods.dev/instructions/aisystant/pack-personal/claude-md"><img src="https://agentmods.dev/badge/instructions/aisystant/pack-personal/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01277 | $0.01277 |
| Opus 5 | $0.00639 | $0.00639 |
| Sonnet 5 | $0.00255 | $0.00255 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
PACK-personal 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 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.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — SPF Personal Pack
Общие инструкции: см.
/Users/tserentserenov/IWE/CLAUDE.mdЭтот файл содержит только специфику данного репозитория.
1. Два слоя репозитория
-
SPF (Second Principles Framework) — фреймворк вторых принципов
- Templates:
/pack/_template/ - Process:
/process/ - Specs:
/spec/
- Templates:
-
Pack "Характеристики и состояния созидателя" — доменное знание
- Folder:
/pack/personal-development/
- Folder:
2. Hard Bans (запреты)
2.1 Запрет дидактики
ЗАПРЕЩЕНО: "step", "lesson", "in N days", "implement", "first/then", "exercise", "module", "week 1", "try this"
ПРИЧИНА: Дидактика — downstream. Pack фиксирует что существует, а не как учить.
2.2 Запрет embeddings как source-of-truth
ЗАПРЕЩЕНО: Хранить vector indexes, embeddings, chunks как канонический контент.
2.3 Запрет "Domain as System"
РАЗЛИЧАЙ: system vs process; method vs tool; work product vs description.
2.4 SoTA — не литобзор
SoTA = статус атрибут (current | deprecated-interpretation | hypothesis) + revision criterion.
3. Структура Pack
/pack/<domain-name>/
00-pack-manifest.md
01-domain-contract/
01A-bounded-context.md
01B-distinctions.md
02-domain-entities/
03-methods/
04-work-products/
05-failure-modes/
06-sota/
07-map/
4. Роль Claude
4.1 Что Claude ДЕЛАЕТ
| Роль | Описание |
|---|---|
| Analyst | Применяет различения к материалам |
| Formalizer | Трансформирует в pack-compliant структуры |
| Process Controller | Следит за lint, hard gates, stages |
| Navigator | Поддерживает maps и cross-references |
4.2 Что Claude НЕ ДЕЛАЕТ
Author— не генерирует знания из ничегоCourse Writer— дидактика в downstreamAutonomous Expert— не решает что истинно
4.3 Информация vs Знание
Material → Extraction Report → Human Review → Approved Candidates → Pack Changes
Claude никогда не трактует информацию как знание.
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 First seen · 162 lines · 1,277 tokens per session scan A 6e2ef49d3b15
PACK-personal CLAUDE.md is an instructions file published in the GitHub repository aisystant/PACK-personal (5 stars, last pushed 3d ago), licensed MIT. It adds 1,277 tokens to every session, about $0.0064 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.