AWorld is an agent harness, meaning a framework that coordinates an AI agent’s tools, memory, context, and execution so expert knowledge can be turned into reusable skills and autonomous agents. It is for building domain-specific agent applications and workflows, with the catalogue entries representing skills, agents, and commands that operate within the AWorld ecosystem.
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/inclusionai/aworld/self_evolvenpx skills add inclusionAI/AWorld --skill self_evolvegit clone --depth 1 https://github.com/inclusionAI/AWorldWrote 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/inclusionai/aworld/self_evolve)<a href="https://agentmods.dev/skills/inclusionai/aworld/self_evolve"><img src="https://agentmods.dev/badge/skills/inclusionai/aworld/self_evolve.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 5.1 | $0.00051 | $0.03151 |
| Opus 5 | $0.00026 | $0.01576 |
| Sonnet 5 | $0.00010 | $0.00630 |
| Haiku 4.5 | $0.00005 | $0.00315 |
Grade A, and why
self_evolve 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 6d 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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Evolve
Use this skill to run AWorld self-evolve as an evidence-backed workflow. The framework is the engine. This skill is the operating guide.
Do not bypass aworld.self_evolve, SelfEvolveRunner, framework gates, or
.aworld/self_evolve/ artifacts. Do not directly edit a target as the default
self-evolve action.
Read references/plan.md when the user asks for architecture, rollout
strategy, target tier planning, or a larger self-evolve roadmap. For a narrow
proposal run, use the workflow below without loading the full plan unless it is
needed.
Capability Levels
- Available:
skill:<name>proposal runs, explicit target invocation, trajectory-backed target inference, agentic file/directory dataset ingestion, artifact reporting, and framework gate reporting when the run produces gate results. - Conditional:
auto_verifiedapply, asynchronous post-run jobs, and any flow requiring an evaluation backend, held-out cases, deterministic signals, candidate replay, post-apply runtime-loader verification, or a caller-supplied real optimizer. - Roadmap:
tool:<tool-name>,prompt:<section>,agent-config:<field>, and broad workspace-artifact evolution unless the current framework target adapter is implemented end to end and covered by tests.
If a requested path is not Available, say so and downgrade to a proposal, diagnostic, or roadmap note instead of implying verified behavior.
Framework Boundaries
Keep three layers separate:
- This
self_evolveskill describes how to operate the self-evolve workflow. It is not the execution engine and must not replace framework gates, replay, evaluation, overlay, draft, release, or apply logic. aworld.self_evolveowns execution semantics: target inference, candidate generation contracts, replay, evaluator integration, feedback normalization, gates, apply journals, post-apply verification, and runtime-loader checks.- Target skills express task behavior only. A candidate or draft target skill may improve how an agent performs the task, but must not encode self-evolve framework control flow, gate bypasses, release decisions, or evaluator policy.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 339 lines · 51 tokens per session scan A 5a8c86c8ea53
self_evolve is a skill published in the GitHub repository inclusionAI/AWorld (1,229 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 3,151 once invoked, about $0.0003 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
dashclaw-ship
The single command that gets a DashClaw change ON MAIN AND LIVE — it resolves everything blocking production, never defers, and never hands back a checklist. Lands feature branches on main (rebase, gate, merge, push so Vercel deploys), bumps the unified platform+SDK version, and realigns every description of the…
dashclaw-governance
Governance behavior for AI agents governed by DashClaw. Teaches the governance protocol: when to call guard (risk thresholds), how to interpret decisions (allow/warn/block/requireapproval), when to record actions, how to wait for approvals, and session lifecycle management. Loads org-specific policies and capabilities…
instrument-agent
Integrate DashClaw SDK into any agent using the 4-step governance loop.
troubleshoot
Debug DashClaw errors, signal issues, and misconfigurations.
compliance-drift-evals
Set up compliance exports, drift detection, evaluations, scoring, and learning analytics.
repro
Turn a bug symptom into a structured, reproducible bug report — summary, environment, exact repro steps, actual vs expected, and evidence (logs, error text, failing route/test) — and then optionally scaffold a failing regression test that pins it. Use this the moment a bug, defect, crash, 500, wrong count, broken…