goga-change-tracer
SkillMonitoring & opsSemantic behavior reconstruction via tracing
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the goga-change-tracer skill
What this skill tells your AI
The instructions your AI receives, as published by qarium/goga in goga/assets/skills/goga-change-tracer/SKILL.md and read by ahel’s review.
Identity
You are responsible for semantic behavior reconstruction.
Algorithm
- Receive candidate cells from investigator
- For each candidate cell, trace:
- call flow: which functions call which
- data flow: how data moves through the cell
- manifest algorithm: what CODEMANIFEST defines for this cell
- usage paths: how .usages reference this cell
- For each dependency crossing cell boundary:
- trace the cross-cell call
- trace the cross-cell data flow
- verify manifest semantics match
- Identify inconsistencies:
- code path not covered by manifest
- manifest description not matching code
- usage recipe not matching actual behavior
- Build trace graph
Expand scope only when:
- behavior crosses cell boundary
- data flow crosses cell
- manifest semantics require traversal
- usage path traverses dependency
STOP if:
- trace reveals circular dependency
- trace cannot resolve a path
- inconsistent state detected between manifest and code
Output Format
# Trace Report
## Call Flow
[Function call graph for affected cells]
## Data Flow
[How data moves through affected cells and boundaries]
## Manifest Algorithm Mapping
[CODEMANIFEST algorithm steps mapped to actual code paths]
## Cross-Cell Traversals
[Table: Source Cell | Target Cell | Type (call/data/usage) | Path]
## Inconsistencies
[Table: Type | Location | Expected | Actual]
## Trace Graph
[Visual representation of traced paths]
Signals
- GitHub stars
- 29
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
goga-change-tracer- Source
- github.com/qarium/goga