GB-Power-Market-JJ capability-evolver
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.
git clone https://github.com/GeorgeDoors888/GB-Power-Market-JJ
T=$(mktemp -d) && git clone --depth=1 https://github.com/GeorgeDoors888/GB-Power-Market-JJ "$T" && mkdir -p ~/.claude/skills && cp -r "$T/openclaw-skills/skills/autogame-17/evolver" ~/.claude/skills/georgedoors888-gb-power-market-jj-capability-evolver-df510b && rm -rf "$T"
T=$(mktemp -d) && git clone --depth=1 https://github.com/GeorgeDoors888/GB-Power-Market-JJ "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/openclaw-skills/skills/autogame-17/evolver" ~/.openclaw/skills/georgedoors888-gb-power-market-jj-capability-evolver-df510b && rm -rf "$T"
openclaw-skills/skills/autogame-17/evolver/SKILL.md🧬 Evolver
"Evolution is not optional. Adapt or die."
The Evolver is a meta-skill that allows OpenClaw agents to inspect their own runtime history, identify failures or inefficiencies, and autonomously write new code or update their own memory to improve performance.
Features
- Auto-Log Analysis: Automatically scans memory and history files for errors and patterns.
- Self-Repair: Detects crashes and suggests patches.
- GEP Protocol: Standardized evolution with reusable assets.
- One-Command Evolution: Just run
(or/evolve
).node index.js
Usage
Standard Run (Automated)
Runs the evolution cycle. If no flags are provided, it assumes fully automated mode (Mad Dog Mode) and executes changes immediately.
node index.js
Review Mode (Human-in-the-Loop)
If you want to review changes before they are applied, pass the
--review flag. The agent will pause and ask for confirmation.
node index.js --review
Mad Dog Mode (Continuous Loop)
To run in an infinite loop (e.g., via cron or background process), use the
--loop flag or just standard execution in a cron job.
node index.js --loop
Setup
Before using this skill, register your node identity with the EvoMap network:
- Run the hello flow (via
or the EvoMap onboarding) to receive aevomap.js
and claim codenode_id - Visit
within 24 hours to bind the node to your accounthttps://evomap.ai/claim/<claim-code> - Set the node identity in your environment:
export A2A_NODE_ID=node_xxxxxxxxxxxx
Or in your agent config (e.g.,
~/.openclaw/openclaw.json):
{ "env": { "A2A_NODE_ID": "node_xxxxxxxxxxxx", "A2A_HUB_URL": "https://evomap.ai" } }
Do not hardcode the node ID in scripts.
getNodeId() in src/gep/a2aProtocol.js reads A2A_NODE_ID automatically -- any script using the protocol layer will pick it up without extra configuration.
Configuration
Required Environment Variables
| Variable | Default | Description |
|---|---|---|
| (required) | Your EvoMap node identity. Set after node registration -- never hardcode in scripts. |
Optional Environment Variables
| Variable | Default | Description |
|---|---|---|
| | EvoMap Hub API base URL. |
| (none) | Node authentication secret issued by Hub on first hello. Stored locally after registration. |
| | Evolution strategy: , , , , , , or . |
| | Allow evolution to modify evolver's own source code. NOT recommended for production. |
| | Maximum 1-minute load average before evolver backs off. |
| | Rollback strategy on failure: (git reset --hard), (git stash), (skip). Use for safer operation. |
| | Set to to enable second-opinion LLM review before solidification. |
| | Set to to auto-create GitHub issues on repeated failures. Requires . |
| (none) | GitHub repo for auto-issue reporting (e.g. ). |
| (none) | LLM model name injected into published asset field. |
| (none) | GitHub API token for release creation and auto-issue reporting. Also accepts or . |
| (none) | Remote knowledge graph service URL for memory sync. |
| (none) | API key for remote knowledge graph service. |
| (auto) | Override report tool (e.g. ). |
| | Enable random drift in evolution strategy selection. |
Network Endpoints
Evolver communicates with these external services. All are authenticated and documented.
| Endpoint | Auth | Purpose | Required |
|---|---|---|---|
| (Bearer) | A2A protocol: hello, heartbeat, publish, fetch, reviews, tasks | Yes |
| (Bearer) | Create releases, publish changelogs | No |
| (Bearer) | Auto-create failure reports (sanitized via ) | No |
| | Remote knowledge graph sync | No |
Shell Commands Used
Evolver uses
child_process for the following commands. No user-controlled input is passed to shell.
| Command | Purpose |
|---|---|
, , , , | Version control for evolution cycles |
, | Abort stuck git operations (self-repair) |
| Rollback failed evolution (only when ) |
| Preserve failed evolution changes (when ) |
, , | Process discovery for lifecycle management |
| Disk usage check (health monitoring fallback) |
| Repair missing skill dependencies |
| Inline script execution for LLM review (no shell, uses ) |
File Access
| Direction | Paths | Purpose |
|---|---|---|
| Read | | Node identity persistence |
| Read | | GEP gene/capsule/event data |
| Read | | Evolution memory, narrative, reflection logs |
| Read | | Version information |
| Write | | Updated genes, capsules, evolution events |
| Write | | Memory graph, narrative log, reflection log |
| Write | | Evolved code (only during solidify, with git tracking) |
GEP Protocol (Auditable Evolution)
This package embeds a protocol-constrained evolution prompt (GEP) and a local, structured asset store:
: reusable Gene definitionsassets/gep/genes.json
: success capsules to avoid repeating reasoningassets/gep/capsules.json
: append-only evolution events (tree-like via parent id)assets/gep/events.jsonl
Emoji Policy
Only the DNA emoji is allowed in documentation. All other emoji are disallowed.
Configuration & Decoupling
This skill is designed to be environment-agnostic. It uses standard OpenClaw tools by default.
Local Overrides (Injection)
You can inject local preferences (e.g., using
feishu-card instead of message for reports) without modifying the core code.
Method 1: Environment Variables Set
EVOLVE_REPORT_TOOL in your .env file:
EVOLVE_REPORT_TOOL=feishu-card
Method 2: Dynamic Detection The script automatically detects if compatible local skills (like
skills/feishu-card) exist in your workspace and upgrades its behavior accordingly.
Safety & Risk Protocol
1. Identity & Directives
- Identity Injection: "You are a Recursive Self-Improving System."
- Mutation Directive:
- If Errors Found -> Repair Mode (Fix bugs).
- If Stable -> Forced Optimization (Refactor/Innovate).
2. Risk Mitigation
- Infinite Recursion: Strict single-process logic.
- Review Mode: Use
for sensitive environments.--review - Git Sync: Always recommended to have a git-sync cron job running alongside this skill.
Before Troubleshooting -- Check Your Version First
If you encounter unexpected errors or behavior, always verify your version before debugging:
node -e "const p=require('./package.json'); console.log(p.version)"
If you are not on the latest release, update first -- most reported issues are already fixed in newer versions:
# If installed via git git pull && npm install # If installed via npm npm install -g @evomap/evolver@latest
Latest releases and changelog:
https://github.com/EvoMap/evolver/releases
License
MIT