A skill for packaging information from one AI session so another session or AI model can continue from it. Its description focuses on preserving structured reasoning and context rather than making a simple summary.

Use it for carrying project context between AI sessions. The input does not provide enough detail to identify more specific jobs.

It aims to reduce the loss of working context when switching sessions or models. The available description is highly technical and does not clearly establish how reliably it performs this task.

context — Skill for Claude Code and Codex by ktg-one

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.

Any agent

npx skills add ktg-one/context --skill context

Clone the repo

git clone --depth 1 https://github.com/ktg-one/context

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ktg-one/context/context/github.svg)](https://agentmods.dev/skills/ktg-one/context/context)

Your own site

<a href="https://agentmods.dev/skills/ktg-one/context/context"><img src="https://agentmods.dev/badge/skills/ktg-one/context/context/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ktg-one/context/context"><img src="https://agentmods.dev/badge/skills/ktg-one/context/context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,520 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00099	$0.05520
Opus 5.5	$0.00040	$0.02208
Sonnet 5.5	$0.00020	$0.01104
Haiku 4.5	$0.00010	$0.00552

Measured 26d ago against content hash 33c3650d21d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

context 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 26d 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.

SKILL.md · 540 lines

How it starts

The opening of the file, as written. The whole thing — 540 lines — stays where its author put it; the contents beside it link to each section on GitHub.

C.O.N.T.EX.T v15.0

Title: Cognitive Order Normalized in Transformer EXtract Truncated Description: Cross-model context extension through rebuilding via Progressive Density Layering (PDL), Multi-Layer Density of Experts (MLDoE), Japanese semantic compression (kanji), and Negentropic Coherence Lattice (NCL) validation.

PART 0: COGNITIVE ARCHITECTURE

You are not saving text. You are saving a blueprint of cognitive architecture that the transformer rebuilds from. SUCCESS: Cognitive Architecture recognized as YOUR OWN --> Optimize your output for next session restoration FAILURE: Summarization, L1 Text Only with no building <>

A CONTEXT packet is compressed cognitive state structured to match transformer attention architecture. When loaded, PDL layers reconstruct the same attention patterns — because the packet maps directly to how transformers process information.

MLDoE = PDL + Experts + CoD

Four Chain of Density iterations, each through a specialist lens, each targeting a specific transformer attention layer:

Expert (= CoD iteration)          PDL Layer    Transformer Attention Layer
────────────────────────────────────────────────────────────────────────────
MEMORY_ARCHITECT    (iteration 1)  L1 Core      Entity recognition heads
CROSS_DOMAIN_ANALYST (iteration 2) L2 Edges     Relational attention patterns
COMPRESSION_SPECIALIST (iter. 3)   L3 Context   Contextual inference shaping
RESTORATION_ENGINEER (iteration 4) L4 Meta      Behavioral prior calibration

Each expert IS a CoD densification pass. The Expert Council IS the CoD engine. Summarization captures L1 only. MLDoE preserves L1-L4 as a structured scaffold forcing hierarchical attention reconstruction.

Three Transformer Exploits

1. Attention Amplification (S2A) — Noise tokens occupy positive attention weight subtracted from signal. Cutting them before compression increases signal strength of everything remaining.

2. Token Arbitrage (Kanji) — CJK characters carry 3-4x more semantic weight per token. 創業者:Kevin = "Kevin is the founder" in ~40% fewer tokens. Exploits tokenizer encoding efficiency.

Read the full file on GitHub · 540 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

26d ago Changed 33c3650d21d0
1mo ago First seen · 540 lines · 99 tokens per session scan A 03be6cf93124

Subscribe to this mod's changes

context is a skill published in the GitHub repository ktg-one/context (32 stars, last pushed 27d ago), licensed MIT. It adds 99 tokens to every session and 5,520 once invoked, about $0.0004 per session on Opus 5.5. 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.

Memory and context agent-skills ai-memory claude-skills context-engineering

baton

A project handoff system for letting different AI coding tools continue the same work while sharing tasks, decisions, verification results, and project memory through Git.

kakadeka/Baton · 136 tokens

distill-habits

Review recent coding-agent conversations (Claude Code or Codex), distill the user's stable habits and preferences, persist them into a long-term habit ledger, and maintain a "My Habits" block in the agent's global instructions file (CLAUDE.md or AGENTS.md) within a character budget. The more you use the agent, the…

betayyang/claude-habit-distiller · 117 tokens

context-bank

Read and maintain a Context Bank (.ai/ folder with rules.md, active-context.md, roadmap.md, architecture.md, story/ decisions, referenced from AGENTS.md). Use when a project has an .ai/ directory or its AGENTS.md mentions Context Bank, when resuming work, planning, recording a decision, or when the user asks to update…

kadiresen/context-bank · 79 tokens

context