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 InternLM/WildClawBench --skill self-improving-agent-3.0.5git clone --depth 1 https://github.com/InternLM/WildClawBenchWrote 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/internlm/wildclawbench/self-improving-agent-3.0.5)<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>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 | $0.00102 | $0.04838 |
| Opus 5 | $0.00051 | $0.02419 |
| Sonnet 5 | $0.00020 | $0.00968 |
| Haiku 4.5 | $0.00010 | $0.00484 |
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.
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.
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.
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 Setup (Recommended)
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
What ships with it
15 files 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.
- _meta.json 139 B
- .learnings/ERRORS.md 75 B
- .learnings/FEATURE_REQUESTS.md 84 B
- .learnings/LEARNINGS.md 99 B
- assets/LEARNINGS.md 1.1 KB
- assets/SKILL-TEMPLATE.md 3.3 KB
- hooks/openclaw/handler.js 1.6 KB runs code
- hooks/openclaw/handler.ts 1.8 KB runs code
- hooks/openclaw/HOOK.md 589 B
- references/examples.md 8.1 KB
- references/hooks-setup.md 4.8 KB
- references/openclaw-integration.md 5.5 KB
- scripts/activator.sh 680 B runs code
- scripts/error-detector.sh 1.3 KB runs code
- scripts/extract-skill.sh 5.2 KB runs code
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.
- 8d ago First seen · 648 lines · 102 tokens per session scan A cec6d90543ea
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.
Other skills, from other repositories
hindsight-architect
Expert memory architect. Understands your application, identifies where memory adds value, and produces an implementation plan with bank config, tag schema, and code.
create-agent
Create a new Hindsight-powered subagent with long-term memory. Use when the user wants a specialized agent that learns and remembers across sessions.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
hindsight-docs
Complete Hindsight documentation for AI agents. Use this to learn about Hindsight architecture, APIs, configuration, and best practices.
hindsight-memory
Long-term memory for the agent via Hindsight. Use to recall relevant past context before answering, retain durable facts as you learn them, and reflect over accumulated memory for the "why" behind a decision. Load whenever continuity across sessions matters — the user refers to earlier work, states a lasting…
hindsight-recall
Search long-term memory for relevant context from past coding sessions using Hindsight MCP tools.