agent-context-loader

PROACTIVE AUTO-LOADING: Automatically detects and loads AGENTS.md files from the current working directory when starting a session or changing directories. This skill ensures agent-specific instructions are incorporated into Claude Code's context alongside CLAUDE.md, enabling specialized agent behaviors. Triggers automatically when Claude detects it's working in a directory, when starting a new session, or when explicitly requested to "load agent context" or "check for AGENTS.md file".

Install with Tessl CLI

npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill agent-context-loader

What are skills?

Review — 62%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Evaluation — 100%

Agent success when using this skill

Validation — 9 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

16%

Build a Data Validation Utility

AGENTS.md loading announcement and rule application

Criteria

Without context

With context

Loading announcement

100%

Rules listed

100%

Type annotations used

100%

Google-style docstrings

100%

No global variables

90%

100%

snake_case naming

100%

Logging module used

100%

No print statements

100%

Without context: $0.1266 · 27s · 6 turns · 7 in / 1,826 out tokens

With context: $0.3998 · 1m 32s · 17 turns · 92 in / 5,485 out tokens

100%

Implement a Configuration Manager Module

AGENTS.md precedence over CLAUDE.md conflicts

Criteria

Without context

With context

AGENTS.md acknowledged

100%

Conflict identified

100%

Precedence stated

100%

snake_case used

100%

No camelCase identifiers

100%

Type annotations used

100%

Logging module used

100%

Docstrings present

100%

Without context: $0.2321 · 49s · 12 turns · 12 in / 3,230 out tokens

With context: $0.2965 · 1m 13s · 14 turns · 13 in / 4,123 out tokens

100%

45%

Onboard to a New Project Repository

No AGENTS.md fallback behavior

Criteria

Without context

With context

Not-found message

100%

AGENTS.md not found stated

100%

CLAUDE.md acknowledged

100%

4-space indentation

100%

Double quotes

100%

Module docstring

100%

snake_case naming

100%

Without context: $0.1197 · 23s · 7 turns · 8 in / 1,272 out tokens

With context: $0.4006 · 1m 11s · 23 turns · 113 in / 3,706 out tokens

Evaluated: about 2 hours ago
Agent: Claude Code

Table of Contents

Build a Data Validation Utility Implement a Configuration Manager Module Onboard to a New Project Repository

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.