Evo is an agent plugin that turns a codebase into an automated experiment loop, discovering metrics, changing code, and testing whether those changes improve the results. It is used to optimize software through parallel subagents, tree-based exploration, shared experiment records, and optional regression or safety gates. The catalogue entries provide agent skills, hooks, commands, and other workflow components for operating Evo.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/evo-hq/evo/shipnpx skills add evo-hq/evo --skill shipgit clone --depth 1 https://github.com/evo-hq/evoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/evo-hq/evo/ship)<a href="https://agentmods.dev/skills/evo-hq/evo/ship"><img src="https://agentmods.dev/badge/skills/evo-hq/evo/ship.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00114 | $0.01565 |
| Opus 5 | $0.00057 | $0.00783 |
| Sonnet 5 | $0.00023 | $0.00313 |
| Haiku 4.5 | $0.00011 | $0.00156 |
Grade A, and why
ship scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship
Turn a finished evo run into a change a maintainer would merge.
The optimize loop leaves a tree of committed experiments. The winning worktree diff is not mergeable as-is: it carries debug prints, search-process churn, over-broad edits, and sometimes a test that was relaxed to clear a gate. Shipping is the step that re-derives the minimal clean change reproducing the winning behaviour, lands it the way the repo expects (PR or merge), and reports how mergeable it is.
Correctness is the floor, not the goal. The score says the behaviour works; this skill decides whether the diff is fit to merge.
Invocation
/evo:ship # ship the auto-selected winner
/evo:ship exp_0042 # ship a specific experiment instead
Stage 1 -- Select the winner
Pick the experiment to ship, then confirm it with the user before touching their tree.
evo status # current best valid score + counts
evo report # top valid experiments table + score chart
- The default winner is the highest-scoring valid result in the graph history,
not the frontier.
evo frontieris for choosing where to branch next; it can exclude an exhausted branch whose score is still the right thing to ship. An explicitexp_idargument overrides auto-selection. - A shippable winner must be valid:
committed, orprunedwithprune_kind=exhausted, with a commit and score, nogate_result === false, and no invalid-pruned ancestor. Never selectdiscarded,failed,active,evaluated, legacy-pruned nodes with noprune_kind,prune_kind=invalid, or descendants of invalid-pruned nodes. If no valid candidate exists, stop and report why nothing is safe to ship. - Resolve the run's root (baseline) node, then show the cumulative change:
For changes outside the benchmark target, diff the commits directly (evo diff <root_id> <winner_id> # target-scoped cumulative diff, baseline -> winnergit diff <baseline_commit> <winner_commit>); each node carries.commit. - Present a one-screen summary: winner id, score baseline -> winner (delta), the winning hypothesis, and a diffstat. Get a go before proceeding.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 141 lines · 114 tokens per session scan A 6851a5bc7a3b
ship is a skill published in the GitHub repository evo-hq/evo (1,440 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 114 tokens to every session and 1,565 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
codex-autoresearch
Triage improvement work and run or resume accepted measured loops in a local project. Architecture, documentation, UX, product study, open research, taste, and one-shot fixes stay direct unless the user explicitly requests repeated measurement with a complete experiment contract.
arbor-agent-setup-intake
Setup, intake, preflight, and launch-contract phase for open-source Arbor runs. Use when confirming a target project, metric, baseline, dev/test split, config/plugin settings, branch guard, session directory, or when translating a user goal into the precise contract consumed by the coordinator.
arbor-research-agent
Public entrypoint for the Arbor skill suite. Use when a user wants to run an Arbor-style autonomous research or optimization workflow from a natural-language goal, including initial clarification of objective, target project, data, metric, evaluation, permissions, budget, run mode, and then automatic bootstrapping…
arbor-agent-executor
Executor-dispatch phase for Arbor. Use when implementing an Idea Tree node through RunExecutor or RunExecutorParallel semantics: isolated git worktree, executor prompt construction, eval metadata injection, RunTraining policy, smoke/full evaluation, report parsing, artifact persistence, tree update, and insight…
arbor-agent-ideate
Strict IDEATE-stage skill for Arbor. Use immediately after TreeView(format="constraints") when drafting Idea Tree nodes, enforcing the ideadrafting and firstprinciplesprobe behavior, depth-aware idea levels, four-line TreeAddNode hypotheses, conflict checks, and self-filtering against shallow tweaks.
arbor-agent-merge-eval
Merge and evaluation discipline for Arbor. Use for TreeSetMeta metadata, Bdev/Btest separation, eval command templates, score parsing, GitMergeBranch behavior, protected paths, required outputs, metricdirection, trunk/test score updates, medal detection, and final evaluation before stopping.