What is self-improving-agent?

A local record-keeping system for saving useful lessons, mistakes, and missing features in a project’s .learnings folder. It keeps these notes separate from the agent’s permanent instruction and memory files.

Use it to log a learning, error, or feature request during development and review those notes before promoting them to longer-term files.

It preserves useful observations without automatically changing long-term behavior or shared instructions. Permanent promotion requires human approval.

self-improving-agent — Skill for Claude Code and Codex by YiShu5

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 YiShu5/claude-skills --skill self-improving-agent

Clone the repo

git clone --depth 1 https://github.com/YiShu5/claude-skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yishu5/claude-skills/self-improving-agent/github.svg)](https://agentmods.dev/skills/yishu5/claude-skills/self-improving-agent)

Your own site

<a href="https://agentmods.dev/skills/yishu5/claude-skills/self-improving-agent"><img src="https://agentmods.dev/badge/skills/yishu5/claude-skills/self-improving-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yishu5/claude-skills/self-improving-agent"><img src="https://agentmods.dev/badge/skills/yishu5/claude-skills/self-improving-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,127 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00068	$0.01127
Opus 5.5	$0.00027	$0.00451
Sonnet 5.5	$0.00014	$0.00225
Haiku 4.5	$0.00007	$0.00113

Measured 2mo ago against content hash ec8875185649, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

self-improving-agent 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 2 executable files (scripts/activator.sh, scripts/error-detector.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-agent/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-Improving Agent (Low-Noise Edition)

A conservative self-improvement system that treats .learnings/ as a write-first cache layer. Nothing reaches the main system files without human review.

Quick Reference

Action	Target	Auto?
Log a learning	`.learnings/LEARNINGS.md`	Yes
Log an error	`.learnings/ERRORS.md`	Yes
Log a feature gap	`.learnings/FEATURE_REQUESTS.md`	Yes
Promote to MEMORY.md	Requires user approval	No
Promote to SOUL.md	Requires user approval + review	No
Promote to AGENTS.md	Requires user approval	No
Promote to TOOLS.md	Requires user approval	No

Core Principles

Write to cache first. All observations go to .learnings/. No exceptions.
Never auto-promote. The cache is not the system. Promotion is a deliberate act.
SOUL.md is sacred. Modifications require explicit human review every time.
MEMORY.md is for stable truths. Only long-term preferences, decisions, and goals belong there.
Errors and learnings stay separate. Different logs, different purposes.
Silence is better than noise. If unsure whether something is worth logging, don't log it.
No cross-session broadcasting of raw learnings. Only promote distilled, verified content.

Logging Format

Learning Entry

## [YYYY-MM-DD] Category: brief title

- **Type**: correction | knowledge_gap | best_practice
- **Context**: What was happening
- **Learning**: What was learned
- **Confidence**: low | medium | high
- **Promote?**: no (default) | candidate | promoted

Error Entry

## [YYYY-MM-DD] brief description

- **Command/Tool**: What failed
- **Error**: The error message or symptom
- **Root Cause**: What actually went wrong
- **Resolution**: How it was fixed
- **Recurrence**: first | repeated

Feature Request Entry

## [YYYY-MM-DD] brief description

- **Gap**: What capability is missing
- **User Need**: Why it matters
- **Priority**: low | medium | high

Read the full file on GitHub · 133 lines

Files

What ships with it

6 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.

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.

2mo ago First seen · 133 lines · 68 tokens per session scan A ec8875185649

Subscribe to this mod's changes

self-improving-agent is a skill published in the GitHub repository YiShu5/claude-skills (132 stars, last pushed 8d ago), licensed MIT. It adds 68 tokens to every session and 1,127 once invoked, about $0.0003 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 2026-08-30.

Building agents Claude Code Memory and context agent-skills ai-workflows automation product-management

self-improving-agent next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
self-improving-agentYiShu5/claude-skills	Skill	132	8d ago	MIT	A	68	Claude Code, Codex
agent-memory-disciplinesickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	36	Claude Code
antigravity-skill-orchestratorsickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	42	Claude Code
agent-memory-mcpsickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	26	Claude Code
agent-memorysickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	18	Claude Code
ai-agents-architectsickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	31	Claude Code
agent-memory-systemssickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	33	Claude Code