ax-annotation

Applies @AX code annotation tags to source files based on trigger conditions and per-file limits.

111|73|Updated Mar 20, 2026
One-click install
npx skills add https://github.com/autopus-ai/autopus-adk --skill ax-annotation-autopus-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ax-annotation
Source: https://github.com/autopus-ai/autopus-adk/tree/main/.omp/skills/ax-annotation
Command: npx skills add https://github.com/autopus-ai/autopus-adk --skill ax-annotation-autopus-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Codebases accumulate unexplained magic constants, untested functions, and fragile high-fan-in symbols that are hard to track. This Skill gives agents a deterministic rule set for inserting @AX:NOTE, @AX:WARN, @AX:ANCHOR, and @AX:TODO tags so code risks and obligations are documented inline and consistently. ## Core Features & Use Cases - Trigger-Based Tagging: Defines concrete detection conditions for each tag type, such as cyclomatic complexity >= 15 for WARN or fan_in >= 3 callers for ANCHOR. - Per-File Limits and Overflow Handling: Enforces a maximum of 3 ANCHOR and 5 WARN tags per file, with downgrade and retention strategies when limits are exceeded. - Lifecycle Tracking: Escalates @AX:TODO tags to WARN after 3 unresolved TDD cycles using @AX:CYCLE counters, and marks all agent-generated tags with an [AUTO] prefix. - Use Case: After finishing a TDD GREEN or REFACTOR phase in a Go project, an agent scans modified files, detects a goroutine launched without context.Context, and inserts // @AX:WARN [AUTO]: ... with a matching @AX:REASON line in the same commit. ## Quick Start Scan the files changed in this task and apply @AX tags according to the trigger rules, respecting per-file limits and the [AUTO] prefix convention.

Frequently Asked Questions about ax-annotation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add @AX annotation tags to my code?▼

Scan the files modified in the current task, check each file against the NOTE, WARN, ANCHOR, and TODO trigger conditions, then insert matching tags with an [AUTO] prefix. Commit the tags together with the code change.

When should I use @AX:WARN versus @AX:NOTE?▼

Use @AX:WARN for risk conditions like goroutines without context.Context, cyclomatic complexity of 15 or more, or global variable mutation, always paired with @AX:REASON. Use @AX:NOTE for explanatory gaps like undocumented magic constants or missing godoc on long exported functions.

What happens when a file exceeds the @AX tag limits?▼

ANCHOR is limited to 3 per file and WARN to 5 per file. Excess ANCHOR candidates are downgraded to NOTE with an explanatory comment, while only the 5 highest-priority WARN entries are retained.

Which programming languages support @AX annotation comments?▼

Go, Java, TypeScript, and Rust use the // comment prefix, Python and Ruby use #, and Haskell uses --. The tag semantics are identical across languages; only the comment syntax changes.

How are stale @AX:TODO tags handled over time?▼

Each TODO carries an @AX:CYCLE counter incremented per TDD cycle. When the count reaches 3 without resolution, the TODO is replaced by a WARN tag with an attached @AX:REASON explaining the escalation.