ai-context

A generator for AGENTS.md and smaller tool-specific instruction files for AI coding assistants.

In plain words
What is it for?
Use it to create, update, audit, or convert context files for Claude Code, Cursor, Copilot, Cline, Windsurf, Gemini CLI, Codex CLI, and OpenCode.
Why use it?
It records project-specific rules that are not obvious from the source code without filling the files with discoverable details, and supports several coding tools.

Skill for Claude CodeCodex

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 skills/littlebearapps/contextdocs/ai-context
Any agent
npx skills add littlebearapps/contextdocs --skill ai-context
Clone the repo
git clone --depth 1 https://github.com/littlebearapps/contextdocs

Made for: Claude Code, Codex.

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,870 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00086 $0.01870
Opus 5 $0.00043 $0.00935
Sonnet 5 $0.00017 $0.00374
Haiku 4.5 $0.00009 $0.00187

Measured 2d ago against content hash 4e5987fbfc0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-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 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.

.claude/skills/ai-context/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Context File Generator

The Signal Gate

Research shows auto-generated context files reduce AI task success by ~3% and increase token costs by 20% (ETH Zurich, Feb 2026). Less is more.

The test for every line: Would removing this cause the AI to make a mistake? If not, cut it.

Include (Non-Discoverable)

  • Non-obvious conventions (import order, naming deviations, spelling locale)
  • Hard constraints ("never use any", "always use direnv exec")
  • Key commands (test, build, deploy, lint)
  • Security rules and environment quirks

Exclude (Discoverable)

Directory listings, dependency lists, architecture overviews, framework conventions, API patterns visible in source, key file tables — agents discover all of these by reading the codebase.

Describe the end state you want, not step-by-step instructions. Consider fixing root causes rather than documenting workarounds (Osmani, 2026).

Line Budgets

File Target Hard Max
AGENTS.md Under 120 lines 160 lines
CLAUDE.md bridge 10-20 lines 80 lines
Other bridge files 10-20 lines 60 lines

Supported Context Files

File Role Purpose
AGENTS.md Canonical Shared identity, commands, conventions, constraints, security notes, monorepo guidance
CLAUDE.md Thin bridge Claude-specific rules + @AGENTS.md import
.cursor/rules/agents.mdc Modern Cursor (default) Frontmatter description, globs, alwaysApply; body imports AGENTS.md
.cursorrules Legacy Cursor Only emitted if already present; ignored by current Cursor in Agent mode
.github/copilot-instructions.md Optional Copilot loads AGENTS.md natively (Aug 2025); only emit for tool-specific scoping
.windsurfrules Compatibility Windsurf rule activation/metadata only
.clinerules/agents.md Modern Cline (default) Directory mode; supports paths: frontmatter for path-scoped rules
.clinerules Legacy Cline Flat-file fallback when already present
GEMINI.md Compatibility Gemini-specific discovery or extension notes only

Read the full file on GitHub · 114 lines

Files

What ships with it

1 file 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.

  1. 2d ago First seen · 114 lines · 86 tokens per session scan A 4e5987fbfc0d

Subscribe to this mod's changes

ai-context is a skill published in the GitHub repository littlebearapps/contextdocs (5 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 1,870 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

skill-creator-primer

You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill. Triggers include creating, editing, reviewing, or contributing to any part of an Agent Skill (description, frontmatter, body, references, scripts, trigger evals, conflicts, etc).

sammcj/agentic-coding · 74 tokens

llm-wiki

Use when building or maintaining a self-contained personal knowledge base (an LLM wiki) in plain markdown. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki health, auditing article claims against their sources, critiquing a wiki source's reasoning, superseding stale knowledge, 'add to…

sammcj/agentic-coding · 82 tokens

apply-mantel-styles

Provides guidelines for applying Mantel's brand styles to diagrams and frontend components. Use when asked to create visuals that need to align with Mantel's branding.

sammcj/agentic-coding · 37 tokens

extract-wisdom

Extract wisdom, insights, and actionable takeaways from YouTube videos, blog posts, articles, or text files. Use when asked to extract wisdom or key insights from a given content source.

sammcj/agentic-coding · 43 tokens

home-assistant

This skill should be used when helping with Home Assistant setup, including creating automations, modifying dashboards, checking entity states, debugging automations, and managing the smart home configuration. Use this for queries about HA entities, YAML automation/dashboard generation, or troubleshooting HA issues.

sammcj/agentic-coding · 57 tokens

aws-strands-agents-agentcore

Use when working with AWS Strands Agents SDK or Amazon Bedrock AgentCore platform for building AI agents. Provides architecture guidance, implementation patterns, deployment strategies, observability, quality evaluations, multi-agent orchestration, and MCP server integration.

sammcj/agentic-coding · 55 tokens