self-improvement

self-improvement is a skill for Claude Code from InternLM/WildClawBench. It costs 102 tokens per session (4,838 once invoked), scanned A, a copy of self-improvement, MIT.

A record-keeping workflow for saving lessons from coding-agent work in Markdown files. It covers failures, user corrections, missing features, outdated knowledge, and better approaches.

In plain words
What is it for?
Use it when commands fail, a user corrects the agent, an external tool breaks, or a repeatable improvement is discovered.
Why use it?
It prevents useful corrections and recurring mistakes from being lost between tasks. The recorded notes can later be turned into project instructions or fixes.

Skill for Claude Code

Written for Claude Code: UserPromptSubmit hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Good fit Use it when commands fail, a user corrects the agent, an external tool breaks, or a repeatable improvement is discovered.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/internlm/wildclawbench/self-improving-agent-3.0.5
Install

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.

Any agent
npx skills add InternLM/WildClawBench --skill self-improving-agent-3.0.5
Clone the repo
git clone --depth 1 https://github.com/InternLM/WildClawBench

Made for: Claude Code.

Wrote 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.

agentmods badge for self-improvement

README.md
[![agentmods](https://agentmods.dev/badge/skills/internlm/wildclawbench/self-improving-agent-3.0.5.svg)](https://agentmods.dev/skills/internlm/wildclawbench/self-improving-agent-3.0.5)
Your own site
<a href="https://agentmods.dev/skills/internlm/wildclawbench/self-improving-agent-3.0.5"><img src="https://agentmods.dev/badge/skills/internlm/wildclawbench/self-improving-agent-3.0.5.svg" alt="Measured on agentmods" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,838 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00102 $0.04838
Opus 5 $0.00051 $0.02419
Sonnet 5 $0.00020 $0.00968
Haiku 4.5 $0.00010 $0.00484

Measured 8d ago against content hash cec6d90543ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

self-improvement 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 8d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (hooks/openclaw/handler.js, hooks/openclaw/handler.ts, scripts/activator.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to self-improvement — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/self-improving-agent-3.0.5/SKILL.md · 648 lines

How it starts

The opening of the file, as written. The whole thing — 648 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-Improvement Skill

Log learnings and errors to markdown files for continuous improvement. Coding agents can later process these into fixes, and important learnings get promoted to project memory.

Quick Reference

Situation Action
Command/operation fails Log to .learnings/ERRORS.md
User corrects you Log to .learnings/LEARNINGS.md with category correction
User wants missing feature Log to .learnings/FEATURE_REQUESTS.md
API/external tool fails Log to .learnings/ERRORS.md with integration details
Knowledge was outdated Log to .learnings/LEARNINGS.md with category knowledge_gap
Found better approach Log to .learnings/LEARNINGS.md with category best_practice
Simplify/Harden recurring patterns Log/update .learnings/LEARNINGS.md with Source: simplify-and-harden and a stable Pattern-Key
Similar to existing entry Link with **See Also**, consider priority bump
Broadly applicable learning Promote to CLAUDE.md, AGENTS.md, and/or .github/copilot-instructions.md
Workflow improvements Promote to AGENTS.md (OpenClaw workspace)
Tool gotchas Promote to TOOLS.md (OpenClaw workspace)
Behavioral patterns Promote to SOUL.md (OpenClaw workspace)

OpenClaw is the primary platform for this skill. It uses workspace-based prompt injection with automatic skill loading.

Installation

Via ClawdHub (recommended):

clawdhub install self-improving-agent

Manual:

git clone https://github.com/peterskoett/self-improving-agent.git ~/.openclaw/skills/self-improving-agent

Remade for openclaw from original repo : https://github.com/pskoett/pskoett-ai-skills - https://github.com/pskoett/pskoett-ai-skills/tree/main/skills/self-improvement

Workspace Structure

OpenClaw injects these files into every session:

~/.openclaw/workspace/
├── AGENTS.md          # Multi-agent workflows, delegation patterns
├── SOUL.md            # Behavioral guidelines, personality, principles
├── TOOLS.md           # Tool capabilities, integration gotchas
├── MEMORY.md          # Long-term memory (main session only)
├── memory/            # Daily memory files
│   └── YYYY-MM-DD.md
└── .learnings/        # This skill's log files
    ├── LEARNINGS.md
    ├── ERRORS.md
    └── FEATURE_REQUESTS.md

Read the full file on GitHub · 648 lines

Changes

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.

  1. 8d ago First seen · 648 lines · 102 tokens per session scan A cec6d90543ea

Subscribe to this mod's changes

self-improvement is a skill published in the GitHub repository InternLM/WildClawBench (516 stars, last pushed 21d ago), licensed MIT. It adds 102 tokens to every session and 4,838 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to self-improvement, differing in 0 lines, and is treated as a copy.