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 skills add majiang213/OpenClaw-MAS --skill cmd_evolvegit clone --depth 1 https://github.com/majiang213/OpenClaw-MASWrote 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/majiang213/openclaw-mas/cmd_evolve)<a href="https://agentmods.dev/skills/majiang213/openclaw-mas/cmd_evolve"><img src="https://agentmods.dev/badge/skills/majiang213/openclaw-mas/cmd_evolve/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/majiang213/openclaw-mas/cmd_evolve"><img src="https://agentmods.dev/badge/skills/majiang213/openclaw-mas/cmd_evolve.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00018 | $0.01154 |
| Opus 5 | $0.00009 | $0.00577 |
| Sonnet 5 | $0.00004 | $0.00231 |
| Haiku 4.5 | $0.00002 | $0.00115 |
Grade A, and why
cmd_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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Path
The first argument is the project path. Before doing anything else:
- Extract the project path from the first argument
- Verify the path exists
- Work within that directory for all file operations and shell commands
Evolve — Memory Clustering and Skill Generation
Reads MEMORY.md, groups related sections by theme, and identifies which clusters
are strong enough candidates to become reusable skills. With --generate, writes
SKILL.md drafts into the project's skills/ directory.
Usage
/skill cmd_evolve <project-path> # Analyze and suggest
/skill cmd_evolve <project-path> --generate # Analyze and write SKILL.md drafts
What to Do
Step 1: Read MEMORY.md
Read ~/.openclaw/workspace-main/MEMORY.md. Parse all ##-level sections —
each section has a heading and a content block.
If MEMORY.md is empty or has fewer than 3 sections, report: "Not enough memory entries to cluster. Add more with /skill cmd_promote." Stop here.
Step 2: Surface recent short-term recalls
openclaw memory search "pattern workflow behavior"
Include any surfaced recalls alongside MEMORY.md sections in the analysis pool.
Step 3: Cluster by theme
Group sections into thematic clusters using:
- Trigger similarity: sections that activate under similar conditions
- Domain overlap: sections touching the same technical area (testing, security, build, etc.)
- Sequential relationship: sections describing steps in a multi-step process
For each cluster, determine:
- Cluster name (descriptive theme)
- Member sections (list of
##headings) - Section count
- Suggested output type:
- command — cluster describes a user-invoked, multi-step workflow
- skill — cluster describes an automatic, pattern-matched behavior
Single-section entries: note them but do not generate from them.
Step 4: Display analysis
============================================================
EVOLVE ANALYSIS
Source: ~/.openclaw/workspace-main/MEMORY.md
Total sections: <N>
Clusters identified: <K>
============================================================
## CLUSTER 1: "<theme name>"
Sections: <count>
Members:
- <heading 1>
- <heading 2>
Suggested type: <command | skill>
Rationale: <one sentence>
## CLUSTER 2: "<theme name>"
...
## SINGLE-SECTION ENTRIES (not enough to cluster)
- <heading>
## SUMMARY
Command candidates: <N>
Skill candidates: <N>
Single entries: <N>
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 · 180 lines · 18 tokens per session scan A 4e958cddffef
cmd_evolve is a skill published in the GitHub repository majiang213/OpenClaw-MAS (5 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 1,154 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
unified-memory
Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.
self-improve
Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…
save-md
Saves a named source to Markdown with provenance and faithful extraction through direct export endpoints. Use when asked to "save this article", "get the markdown", "transcribe this", or "keep this source". A URL supplied as task context alone does not trigger conversion; a chat summary stays in chat.
knowledge-base
Retrieves and updates project-specific prompt knowledge from comparison evidence and user feedback. Use only for prompt analysis or post-comparison learning within a Rashomon evaluation.
swarmclaw
AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.
obs-memory
Persistent Obsidian-based memory for coding agents. Use at session start to orient from a knowledge vault, during work to look up architecture/component/pattern notes, and when discoveries are made to write them back. Activate when the user mentions obsidian memory, obsidian vault, obsidian notes, or /obs commands.…