autocontext

autocontext is a plugin for Claude Code from jamditis/claude-skills-journalism. Its manifest loads nothing; the 5 commands, 1 agent it bundles cost 66 tokens per session together, scanned A, original, MIT.

A project-knowledge plugin that saves lessons and makes them available across coding sessions and developers. It uses structured lessons and hooks, which are automatic points where project actions can trigger stored guidance.

In plain words
What is it for?
Recording project lessons and carrying shared knowledge between developers and coding-agent sessions.
Why use it?
Important decisions and discoveries do not have to be rediscovered by each person or in every new session.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add jamditis/claude-skills-journalism
agentmods
npx agentmods add plugins/jamditis/claude-skills-journalism/autocontext
Clone the repo
git clone --depth 1 https://github.com/jamditis/claude-skills-journalism

Made for: Claude Code.

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 autocontext

README.md
[![agentmods](https://agentmods.dev/badge/plugins/jamditis/claude-skills-journalism/autocontext.svg)](https://agentmods.dev/plugins/jamditis/claude-skills-journalism/autocontext)
Your own site
<a href="https://agentmods.dev/plugins/jamditis/claude-skills-journalism/autocontext"><img src="https://agentmods.dev/badge/plugins/jamditis/claude-skills-journalism/autocontext.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 5 commands, 1 agent cost 66 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

autocontext 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 5d 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.

autocontext/.claude-plugin/plugin.json · 10 lines

What it actually says

{
  "name": "autocontext",
  "version": "1.1.2",
  "description": "Accumulates project knowledge across sessions and developers through structured lessons and hooks",
  "author": {
    "name": "Joe Amditis",
    "email": "[email protected]"
  }
}
Contents

What it installs

The manifest is a name and a version. 5 commands, 1 agent travel with it, and installing the plugin installs all of them — 66 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 5d ago First seen · 10 lines scan A d75171264829

Subscribe to this mod's changes

autocontext is a plugin published in the GitHub repository jamditis/claude-skills-journalism (384 stars, last pushed 7d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Related

Other plugins, from other repositories

knowledge-and-memory

Research methodology, corpus search, persistent memory, iterative workflows, and project knowledge management.

oaustegard/claude-skills · not measured

obsidian

Plugin สำหรับคลังความรู้แบบ markdown ที่เก็บนอก repo ครอบคลุม Skill Cookbook รวบรวมเทคนิคการใช้งานเครื่องมือ AI CLI/Tools ต่างๆ (Claude Code CLI, Claude Design, Codex CLI, Antigravity CLI) เพิ่มเทคนิคใหม่ได้เรื่อยๆ ทั้งจากผู้ใช้เองและสั่งให้ Claude ค้น/อัพเดทให้.

natthasath/natthasath-marketplace · not measured

lore

Persistent project knowledge base for Claude Code. Records current state, phased roadmap, decisions and their rejected alternatives, and failed approaches — so a new session resumes from what was recorded instead of re-reading the whole codebase.

sh008/claude-lore · not measured

context-degradation

Patterns for recognizing and mitigating context failures in LLM agents. Covers lost-in-middle, context poisoning, distraction, confusion, clash, and model-agnostic degradation measurement.

viktorbezdek/skillstack · not measured

context-optimization

Techniques for extending effective context capacity through compaction, observation masking, KV-cache optimization, and context partitioning. Double or triple effective context without larger models.

viktorbezdek/skillstack · not measured

rigorous-paper-reviewer

Deep 7-pass technical review of LaTeX papers — structure, notation, theorem/proof, numerics, complexity, figures, coherence. Includes a static Python verifier for automated triage of labels, cross-references, and structure.

shubham0704/claude-skills · not measured