Legioni vs Skills

Legioni and Skills are both cli coding agents tracked by AIDiveForge. Below is a side-by-side comparison of pricing, capabilities, platforms, and ownership — sourced from each tool's live website and verified before publishing.

Legioni

The orchestrator receives a plain-language task in opencode, breaks it down, and hands it to a chain of specialist agents — architect, implementer, reviewer, test-strategist — in sequence. Each step feeds the next; the loop closes only when tests pass. The 'lesson promotion' mechanism lets teams encode what they learn into persistent agent behavior, so the same mistake doesn't resurface two projects later. The hard boundary: Legioni runs inside opencode, full stop. If your team is not already on opencode or cannot adopt it, the architecture is irrelevant — there is no standalone path and no API to route through a different runtime.

Skills

Orbit is a CLI harness that wraps any JSON-speaking coding agent — Claude, Codex, Cursor, or your own — in a bounded loop: one task selected from a dependency-ordered backlog, executed by the agent, then checked against tests, lint, and type validation before the orbit closes. If the agent cannot prove the work, the run does not advance. Every orbit writes structured JSON artifacts and a human-readable progress log, so you are reviewing evidence rather than re-reading diffs and guessing. The harness runs entirely locally, requires no API key for the replay demo, and is MIT licensed. Where it breaks: teams whose validation needs go beyond tests and lint — custom scoring rubrics, multi-step human approval workflows, or large parallel backlogs — will find the intentionally small surface area a ceiling rather than a feature.

Attribute	Legioni	Skills
Pricing	Free	Free
Free trial	No	No
Open source	Yes	Yes
Has API	No	No
Self-hosted option	Yes	Yes
Platforms	npm, Node.js	Cross-platform (Python 3.6+)
Pros	Test-driven agent loop closes only when tests pass, so you are not manually checking whether the implementer's output actually works before shipping it to review. Specialist agents handle discrete roles — architecture, implementation, review, test strategy — which means a single task does not collapse into one undifferentiated prompt that loses track of constraints halfway through. Lesson promotion persists learned behaviors across sessions and projects, so teams stop re-encoding the same project rules every time they open a new task. Zero-install path via npx means you can run `legioni init` in a new repo without touching your global Node environment, keeping adoption friction low for the first experiment. MIT license and self-hosted operation mean the agents run entirely within your environment — no usage data leaves to a vendor API beyond whatever opencode itself sends.	Validation gates block an orbit from closing unless tests, lint, and type checks pass, so you stop merging agent output that ran without error but failed to do what the task required. Four structured artifacts per run — result, evaluation, review recommendation, and a progress log — give you an auditable evidence trail, so post-mortem debugging is reading JSON rather than reconstructing what the agent did from git history. Agent-neutral CLI contract means you can run Claude and Codex against the same task and backlog, comparing scored artifacts directly instead of running separate experiments with incomparable outputs. Dependency-ordered backlog selection keeps each orbit focused on one task at a time, so the agent cannot silently absorb scope from adjacent work and produce diffs that are hard to attribute. MIT licensed with a no-API-key replay demo, so you can evaluate the full validation loop against a real artifact chain without committing credentials or incurring cost.
Cons	Legioni is a hard dependency on opencode: every agent, every loop, every lesson runs inside opencode's runtime. Teams on Cursor, Cline, or any other AI coding environment cannot use this tool — the only path forward is adopting opencode first, which is a separate adoption decision with its own trade-offs. The project's public repository shows five commits and a small star count, which means edge cases in the agent loop, lesson promotion conflicts, and stack detection failures are under-documented and under-reported. Teams hitting unexpected behavior have no community issue history to search and no support channel beyond filing a GitHub issue themselves. Lesson promotion is a manual, explicit action — the agents do not automatically surface or apply learned behaviors without team intervention. Projects where nobody curates the promoted lessons see no compounding benefit across sessions, which makes the core differentiating feature opt-in rather than default.	Validation is limited to tests, lint, and type checks as described on the vendor page — teams whose definition of 'done' includes semantic correctness, security scanning, or domain-specific rules have to build that checking outside the harness and wire it in manually, adding a second system to maintain. The harness executes one orbit at a time; teams running large backlogs where tasks are independent and could parallelize will hit a throughput ceiling and move to a more capable orchestration layer or build parallelism themselves. There is no built-in multi-step human approval workflow beyond the accept/iterate/stop recommendation in `review.json` — teams that need a formal sign-off gate before code advances to staging will need to script that around the harness or switch to a tool that treats human review as a first-class execution step.

Bottom line

Legioni and Skills are closely matched on pricing model, openness, and API availability — pick by feature set and platform support in the table above.

Frequently asked questions

What is the difference between Legioni and Skills?

Legioni is Free and open source, while Skills is Free and open source. Compare pricing, free trial, API, platforms, and pros/cons in the table above on AIDiveForge.

Is Legioni better than Skills?

It depends on your workflow. Use the side-by-side attributes (pricing, open source, API, self-hosted, platforms) to decide. AIDiveForge does not rank a universal winner — we publish verified facts so you can choose.