Task Inline
SkillProductivityImplement and self-review a small, local code change without spawning planner, test-writer, implementer, or reviewer agents. Use only when the user explicitly invokes task-inline for a trivial correction that does not require new behavioral tests or independent review.
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 Task Inline skill
What this skill tells your AI
The instructions your AI receives, as published by cartanova-ai/sonamu in .agents/skills/task-inline/SKILL.md and read by ahel’s review.
The main orchestrator performs the work directly. Do not spawn sub-agents.
Procedure
- Inspect the target code and applicable repository or framework skills.
- Implement the smallest direct change.
- Run existing focused validation when available.
- Re-read the final diff and check:
- It matches the requested correction.
- It contains no unrelated changes.
- It introduces no obvious runtime or type error.
- It does not unintentionally change existing behavior.
- Report changed files, validation, and any unverified risk.
Do not add new tests unless the user explicitly includes test work.
Escalate to task
Stop and ask the user to switch to the normal task workflow when the work
reveals:
- New user-visible behavior or an API contract change
- Data persistence, authorization, migration, transaction, or concurrency work
- A regression risk that needs a new test
- A materially larger scope than the user described
Do not silently upgrade or downgrade workflows.
Signals
- GitHub stars
- 22
- Forks
- 7
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
task-inline- Source
- github.com/cartanova-ai/sonamu