self-improvement

self-improvement is a skill for Claude Code from bl1nk-bot/bl1nk-agents-manager. It costs 122 tokens per session (7,382 once invoked), scanned A, original, MIT.

A practice for recording errors, user corrections, missing features, outdated knowledge, and better approaches in Markdown files. Important general lessons can also be promoted into project instructions.

In plain words
What is it for?
Use it after failed commands, corrections, tool failures, knowledge gaps, or repeated workflow improvements to maintain a project learning log.
Why use it?
It prevents the same mistakes and discoveries from being forgotten between tasks. It gives coding agents a written record they can use for future work.

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 after failed commands, corrections, tool failures, knowledge gaps, or repeated workflow improvements to maintain a project learning log.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bl1nk-bot/bl1nk-agents-manager/self-improving
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 bl1nk-bot/bl1nk-agents-manager --skill self-improving
Clone the repo
git clone --depth 1 https://github.com/bl1nk-bot/bl1nk-agents-manager

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/bl1nk-bot/bl1nk-agents-manager/self-improving/github.svg)](https://agentmods.dev/skills/bl1nk-bot/bl1nk-agents-manager/self-improving)
Your own site
<a href="https://agentmods.dev/skills/bl1nk-bot/bl1nk-agents-manager/self-improving"><img src="https://agentmods.dev/badge/skills/bl1nk-bot/bl1nk-agents-manager/self-improving/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.

agentmods 80×15 button for self-improvement

Your own site · 80×15
<a href="https://agentmods.dev/skills/bl1nk-bot/bl1nk-agents-manager/self-improving"><img src="https://agentmods.dev/badge/skills/bl1nk-bot/bl1nk-agents-manager/self-improving.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,382 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 original No closer match found 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 $0.00122 $0.07382
Opus 5.5 $0.00049 $0.02953
Sonnet 5.5 $0.00024 $0.01476
Haiku 4.5 $0.00012 $0.00738

Measured 2mo ago against content hash 3b22e34967f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo ago.

The scan reads SKILL.md. This mod also ships 5 executable files (hooks/handler.js, hooks/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.

skills/self-improving/SKILL.md · 642 lines

How it starts

The opening of the file, as written. The whole thing — 642 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ทักษะการปรับปรุงตนเอง (Self-Improvement Skill)

บันทึกการเรียนรู้และข้อผิดพลาดลงในไฟล์ Markdown เพื่อการปรับปรุงอย่างต่อเนื่อง Agent ที่เขียนโค้ดสามารถนำสิ่งเหล่านี้ไปประมวลผลเพื่อแก้ไข และการเรียนรู้ที่สำคัญจะถูกส่งเสริมไปยังหน่วยความจำของโครงการ

ข้อมูลอ้างอิงฉบับย่อ

สถานการณ์ การดำเนินการ
คำสั่ง/การดำเนินการล้มเหลว บันทึกลงใน .learnings/ERRORS.md
ผู้ใช้แก้ไขคุณ บันทึกลงใน .learnings/LEARNINGS.md พร้อมหมวดหมู่ correction
ผู้ใช้ต้องการคุณสมบัติที่ขาดหายไป บันทึกลงใน .learnings/FEATURE_REQUESTS.md
API/เครื่องมือภายนอกล้มเหลว บันทึกลงใน .learnings/ERRORS.md พร้อมรายละเอียดการรวม
ความรู้ล้าสมัย บันทึกลงใน .learnings/LEARNINGS.md พร้อมหมวดหมู่ knowledge_gap
พบแนวทางที่ดีกว่า บันทึกลงใน .learnings/LEARNINGS.md พร้อมหมวดหมู่ best_practice
ทำให้รูปแบบที่เกิดซ้ำง่ายขึ้น/แข็งแกร่งขึ้น บันทึก/อัปเดต .learnings/LEARNINGS.md ด้วย Source: simplify-and-harden และ Pattern-Key ที่เสถียร
คล้ายกับรายการที่มีอยู่ เชื่อมโยงกับ **See Also**, พิจารณาเพิ่มลำดับความสำคัญ
การเรียนรู้ที่ใช้ได้ในวงกว้าง ส่งเสริมไปยัง CLAUDE.md, AGENTS.md, และ/หรือ .github/copilot-instructions.md
การปรับปรุงขั้นตอนการทำงาน ส่งเสริมไปยัง AGENTS.md (OpenClaw workspace)
ข้อควรระวังของเครื่องมือ ส่งเสริมไปยัง TOOLS.md (OpenClaw workspace)
รูปแบบพฤติกรรม ส่งเสริมไปยัง SOUL.md (OpenClaw workspace)

การตั้งค่า OpenClaw (แนะนำ)

OpenClaw เป็นแพลตฟอร์มหลักสำหรับ skill นี้ โดยใช้การฉีด prompt แบบ workspace พร้อมการโหลด skill อัตโนมัติ

การติดตั้ง

Via ClawdHub (recommended):

clawdhub install self-improving-agent

Manual:

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

สร้างใหม่สำหรับ OpenClaw จาก repo ต้นฉบับ: https://github.com/pskoett/pskoett-ai-skills - https://github.com/pskoett/pskoett-ai-skills/tree/main/skills/self-improvement

โครงสร้าง Workspace

OpenClaw จะแทรกไฟล์เหล่านี้ในทุกเซสชัน:

Read the full file on GitHub · 642 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. 2mo ago First seen · 642 lines · 122 tokens per session scan A 3b22e34967f3

Subscribe to this mod's changes

self-improvement is a skill published in the GitHub repository bl1nk-bot/bl1nk-agents-manager (8 stars, last pushed yesterday), licensed MIT. It adds 122 tokens to every session and 7,382 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.

Related

Other skills, from other repositories

stack-trace-rust-probe

Internal helper for meta-stack-trace-investigator. Use when a Rust panic or backtrace needs Rust-specific Result/Option checks, cargo test guidance, and patch targets.

opensquilla/opensquilla · 42 tokens

omh-rust

This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).

rlaope/oh-my-hermes · 74 tokens

harbor

Run Terminal-Bench or any Harbor dataset with Ante as the agent, using the Harbor adapter in the ante repo's ante-harbor/ directory. Use when the user wants to benchmark Ante on Harbor or reproduce Ante's published eval results.

AntigmaLabs/ante · 51 tokens

simplify

Clean up changed code while preserving intended behavior. Use when the user asks to simplify or improve code quality through reuse, simplification, efficiency, and abstraction reviews. Correctness bug hunting is outside scope.

AntigmaLabs/ante · 43 tokens

yoagent

Use when building, extending or upgrading an agent on the yoagent Rust crate. Maps each job (tools, policies, verifiers, budgets, sub-agents, plugins from other ecosystems, retries, structured output, tests) to the yoagent feature for it, with tips, pitfalls and what changed per version.

yologdev/yoagent · 66 tokens

sivtr-memory

Retrieve shared local work memory: terminal activity, AI conversation history, prior decisions, validation evidence, debugging trails, recaps, and handoff context. Use before asking the user to repeat local work context.

Ariestar/sivtr · 46 tokens