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-loader68
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/skillAgent success when using this skill
Validation for skill structure
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured description that clearly communicates when the skill should trigger and its specific purpose around AGENTS.md files. The main weakness is that the actual capabilities could be more concrete - it describes the loading mechanism but not what specific actions or behaviors result from it. The trigger terms and completeness are strong points.
Suggestions
Add more specific concrete actions that result from loading AGENTS.md, such as 'parses agent configuration', 'applies role-specific prompts', or 'configures tool permissions'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AGENTS.md files) and describes actions like 'detects and loads' and 'ensures agent-specific instructions are incorporated', but the actual concrete actions are somewhat abstract - it doesn't specify what happens after loading or what 'specialized agent behaviors' means in practice. | 2 / 3 |
Completeness | Clearly answers both what ('detects and loads AGENTS.md files', 'ensures agent-specific instructions are incorporated') and when ('when starting a session', 'changing directories', 'explicitly requested to load agent context'). Has explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes good natural trigger terms: 'load agent context', 'check for AGENTS.md file', 'starting a session', 'changing directories'. These are phrases users would naturally say when needing this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche focused on AGENTS.md files specifically, distinct from general file handling or CLAUDE.md skills. The specific file type and auto-loading behavior create a clear, non-conflicting scope. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is significantly over-engineered for its purpose. It explains the same auto-loading concept repeatedly across multiple sections, includes unnecessary 'Benefits' marketing copy, and provides an overly detailed example AGENTS.md that belongs in separate documentation. The core instruction (check for AGENTS.md, read it, apply rules) could be conveyed in under 30 lines.
Suggestions
Reduce to essential content: trigger conditions, the 3-step execution flow with actual executable code, and conflict resolution rules - remove Benefits, User Experience, and verbose explanations
Move the 'Example AGENTS.md Structure' to a separate reference file and link to it
Add validation step: verify AGENTS.md parses correctly before applying rules, with error handling for malformed content
Replace pseudocode in Implementation Details with actual executable commands or remove the section entirely if Claude already knows how to read files
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with excessive repetition. The same concepts (auto-loading, trigger conditions, AGENTS.md vs CLAUDE.md) are explained multiple times. Contains unnecessary sections like 'Benefits' and 'User Experience' that restate obvious information. The skill could be reduced to ~30% of its current length. | 1 / 3 |
Actionability | Provides some concrete guidance (bash check, Read tool usage) but much is pseudocode or conceptual. The 'Implementation Details' section mixes executable commands with vague instructions like 'Load full content into session context' and 'Treat AGENTS.md content as...' which aren't actionable. | 2 / 3 |
Workflow Clarity | Steps are listed (Check → Read → Apply) but lack validation checkpoints. No error handling for malformed AGENTS.md content, no verification that rules were correctly applied, and the 'Troubleshooting' section is reactive rather than preventive. | 2 / 3 |
Progressive Disclosure | References related features (slash command, hook script) but doesn't link to separate documentation. The 'Example AGENTS.md Structure' section is lengthy inline content that could be a separate reference file. Overall structure exists but content that should be separate is inline. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Reviewed
Table of Contents
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.