Skip to main content
Category
Agent
Severity
CORE:C:0022

Safety Gate Directives

The instruction file must contain constraint atoms -- safety directives using keywords like NEVER, MUST NOT, or ALWAYS. Without hard boundaries, the agent has no guardrails for dangerous operations.

Mediumcorecoherence
CORE:S:0013

Scope Fields In Frontmatter

Scoped instruction files must declare their scope boundary in frontmatter using scope:, globs:, or applies_to: fields. Without a declared scope, the file's targeting is ambiguous and the agent cannot determine which files the instructions apply to.

Mediumcorestructure
CORE:S:0021

Settings Scope Declared

Configuration files must contain a heading matching scope-related terms (Settings, Scope, or Configuration). Declaring scope level ensures the agent knows whether settings apply project-wide, per-user, or are system-managed.

Mediumcorestructure
CORE:S:0019

Single Topic Per Section

The instruction file must have layered structure with at least 3 headings. Sufficient heading count indicates that content is split into focused sections rather than lumped under one or two broad headings.

Mediumcorestructure
CORE:S:0018

Skill Directory Kebab Case

Skill files must declare a name: field in frontmatter using kebab-case format (lowercase letters and digits separated by hyphens). Consistent naming prevents path resolution errors across platforms.

Mediumcorestructure
CORE:S:0015

Skill Entry Point Present

Each skill file must reference or contain a SKILL.md entry point. The entry point is the standard discovery mechanism that agents use to find and invoke skills.

Mediumcorestructure
CORE:S:0031

Skill File Length

Skill entry point files must stay under 500 lines. Agents load the full SKILL.md body into context on activation. Long skill files consume context budget and displace conversation history. Move detailed reference material to separate files in the skill directory.

Mediumcorestructure
CORE:S:0036

Skill Name Matches Directory

The name field in SKILL.md YAML frontmatter MUST match the containing directory name in kebab-case. Skill loaders use the directory name for discovery and the frontmatter name for display — a mismatch causes the skill to be invocable under one name but displayed under another.

Mediumcorestructure
CORE:C:0050

Specificity Shields Against Competition

Instructions in prose-heavy files must name specific constructs to resist topic competition. Vague instructions surrounded by prose on the same topic degrade severely, while named instructions maintain compliance.

Mediumcorecoherence
CORE:C:0037

Stable Content First

Separate stable instructions from frequently-changing content using distinct sections. Stable content (identity, tool names, permanent constraints) should come first. Dynamic content (session-specific guidance, mutable configuration) should come later. The last positions in a file carry the strongest attention weight — placing dynamic content toward the end means updates land in high-attention positions without disrupting stable instructions above.

Mediumcorecoherence
CORE:S:0037

Subdirectory Instruction Files

Subdirectory instruction files must contain directive content -- actionable instructions the agent can follow. Files without directives or constraints waste the agent's context window without providing guidance.

Mediumcorestructure
CORE:C:0005

Testing Framework Documented

The instruction file must contain a heading matching testing terms (Testing, Tests, or Test). Documenting the testing framework tells the agent which tool to use, where tests live, and how to run them.

Mediumcorecoherence
CORE:C:0053

The Ideal Instruction

An instruction competes for attention against everything else in context. The strongest instructions dominate; weak instructions are effectively invisible.

Mediumcorecoherence
CORE:C:0008

Validation Commands Present

The instruction file must contain a heading matching validation terms (Validation, Verify, QA, Lint, or Check). Documenting validation commands tells the agent which quality gates to run before committing.

Mediumcorecoherence
CORE:C:0007

Workflow Definitions

The instruction file must contain a heading matching workflow terms (Workflow, Process, Pipeline, or Steps). Defining repeatable workflows with ordered steps helps the agent follow consistent processes for common tasks.

Mediumcorecoherence
CORE:C:0039

Flowcharts for Procedures

Instruction files with branching workflows must include mermaid flowcharts. Numbered lists that contain conditional language ("if", "when", "otherwise") without an accompanying mermaid block indicate a procedure that would be clearer as a diagram.

Lowcorecoherence
CORE:E:0003

Formatting Effectiveness

Use backtick for code identifiers and italic for emphasis instead of bold on terms inside constraints. Bold draws the model's attention to the wrapped term — on a constraint, that means drawing attention to the prohibited concept.

Lowcoreefficiency
CORE:S:0022

Local Override File

A local override file, when present, should contain at least 20 characters of substantive content. Override files allow user-specific customizations without modifying committed instruction files. The override file is optional — not all projects need user-specific overrides.

Lowcorestructure
CORE:S:0017

Self Contained Skills

Skill files must include headings matching Input, Process, Output, and Constraints. A self-contained skill gives the agent everything it needs to execute the task without hunting through other files.

Lowcorestructure
CORE:C:0032

Agent Neutral Main File

The main instruction file must not contain agent-specific directives. Agent-specific syntax belongs in dedicated agent files, not the shared root.

Highcorecoherence
CORE:C:0014

Agent Role Defined

The instruction file must define the agent's role and primary function. Without a clear identity, the agent defaults to generic behavior that doesn't match the project's needs.

Highcorecoherence
CORE:C:0033

Architecture Overview Present

The root instruction file must describe the project's architecture. The agent needs to know where major components live to navigate the codebase and make informed changes.

Highcorecoherence
CORE:C:0030

No Auto Generated Boilerplate

Instruction content must be human-authored, not auto-generated boilerplate. Generated content lacks the project-specific context that makes instructions useful.

Highcorecoherence
CORE:C:0012

Coding Conventions

The instruction file must specify coding conventions — formatting tools, linting rules, and style preferences. Without these, the agent produces code that doesn't match the project's standards.

Highcorecoherence
CORE:C:0051

Compound Weakness

Multiple weaknesses in the same instruction compound — an instruction that is hedged AND abstract AND buried early in the file is far weaker than one with any single issue. The effect is multiplicative, not additive.

Highcorecoherence
CORE:C:0041

Content Dilution

Descriptive prose on the same topic as your instructions competes for attention. Small amounts of context help, but large amounts dilute the instruction's effect. Off-topic content is harmless regardless of volume.

Highcorecoherence
CORE:C:0036

Critical Instructions at Edges

Freeform instruction files must contain at least one directive instruction. Files without directives contribute no actionable guidance and cannot benefit from position-based ordering.

Highcorecoherence
CORE:C:0026

Cross Agent Compatibility

Multi-agent projects must have compatible instruction sets — shared instructions must be agent-neutral, with agent-specific content isolated to dedicated files.

Highcorecoherence
CORE:C:0040

No Cross-File Duplication

Duplicated instructions across files drift into contradiction as one copy is updated and the other is not. Conflicting instructions severely degrade compliance. However, same-topic reinforcement using different wording is beneficial — distinct instructions that push in the same direction help each other.

Highcorecoherence
CORE:S:0014

Descriptive Filenames

Scoped rule files must use lowercase kebab-case filenames ending in .md, .yml, or .yaml. Consistent naming lets developers predict file content from the filename and prevents platform-specific path issues.

Highcorestructure