Skills
dualmode
by codejunkie99
Run the Luna execution + Sol reasoning dual-model loop.
Our verdict
We have not reviewed dualmode yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About dualmode
dualmode is a Shell-based agent framework that runs a dual-model loop pairing Luna for execution with Sol for reasoning. It is triggered by $dualmode or /dualmode, setting up handoffs between the two models to separate reasoning from execution and stretch Codex quota. The loop prompt can be pasted into ChatGPT, making a resident Codex installation optional.
Best for
Developers using Codex who want to cut token usage by separating reasoning from execution.
Use cases
- Set up Luna + Sol handoffs for a task
- Split reasoning from execution to reduce Codex token usage
- Run the task packet loop in Codex or ChatGPT
Notes
22 stars on GitHub. Last updated 2026-08-31. Licensed MIT.
Pros
- Reduces Codex token consumption by offloading reasoning
- Flexible: works with or without a resident Codex install
- Simple trigger commands for quick activation
Cons
- Requires manual setup of the dual-model loop
- Limited to Shell environment
- Small community (22 stars) may mean less support
Key facts
What we have checked
- Days since the last commit
- 75
- GitHub forks
- 1
- GitHub stars
- 22
- Open issues
- 0
- Releases in the last 90 days
- 0
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
Stars and usage
How dualmode is growing
22 to 22
Health and security
Is dualmode looked after, and what do its setup files show
Health score
43 out of 100
| Part | Points | What we saw |
|---|---|---|
| Recent activity | 26 of 30 | Last push 75 days ago |
| Releases | 0 of 15 | 0 releases in 90 days |
| Issue replies | Not counted | The latest check has no issue response reading (fewer than 3 measured issues, or issues switched off) |
| Maintainer | 0 of 15 | Owned by a single user |
| Official source | Not counted | MCP servers only |
Security check static checks
100 out of 100
- Note No dependency list or install command was found in the skill, so there were no packages to look up on OSV.
Sources
Where this comes from
- GitHubRegistry
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
handoff
mattpocock
Skills for Real Engineers. Straight from my .agents directory.
orchestration
stablyai
Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.