self-improving-agent

self-improving-agent is a skill for Claude Code from 1mancompany/OneManCompany. It costs 53 tokens per session (3,184 once invoked), scanned B, original, Apache-2.0.

A system that records what an AI agent learns while using skills and applies those lessons to later work. It uses several kinds of memory for general knowledge, past experiences, and current tasks.

In plain words
What is it for?
Use it to learn from skill completions and errors, trigger checks around skill events, and track where improvements came from.
Why use it?
It aims to reduce repeated mistakes by detecting guidance problems, correcting them, and checking whether the guidance still works.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

Good fit Use it to learn from skill completions and errors, trigger checks around skill events, and track where improvements came from.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/1mancompany/onemancompany/self-improving-agent
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 1mancompany/OneManCompany --skill self-improving-agent
Clone the repo
git clone --depth 1 https://github.com/1mancompany/OneManCompany

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-improving-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/1mancompany/onemancompany/self-improving-agent/github.svg)](https://agentmods.dev/skills/1mancompany/onemancompany/self-improving-agent)
Your own site
<a href="https://agentmods.dev/skills/1mancompany/onemancompany/self-improving-agent"><img src="https://agentmods.dev/badge/skills/1mancompany/onemancompany/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.

agentmods 80×15 button for self-improving-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/1mancompany/onemancompany/self-improving-agent"><img src="https://agentmods.dev/badge/skills/1mancompany/onemancompany/self-improving-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,184 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 7 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Data Exfiltration · line 84
    Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.
    Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
  • high Rogue Agent · line 85
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • high Rogue Agent · line 90
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • high Rogue Agent · line 294
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • high Rogue Agent · line 386
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • high Rogue Agent · line 390
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • high Agent Snooping · line 323
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.03184
Opus 5 $0.00026 $0.01592
Sonnet 5 $0.00011 $0.00637
Haiku 4.5 $0.00005 $0.00318

Measured 13d ago against content hash ed0d4a70e034, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

self-improving-agent scanned grade B with 1 finding 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 13d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (hooks/post-bash.sh, hooks/pre-tool.sh, hooks/session-end.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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Add to Claude Code settings (`~/.claude/settings.json`):
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

company/human_resource/employees/00002/skills/self-improving-agent/SKILL.md · 409 lines

How it starts

The opening of the file, as written. The whole thing — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-Improving Agent

"An AI agent that learns from every interaction, accumulating patterns and insights to continuously improve its own capabilities." — Based on 2025 lifelong learning research

Overview

This is a universal self-improvement system that learns from ALL skill experiences, not just PRDs. It implements a complete feedback loop with:

  • Multi-Memory Architecture: Semantic + Episodic + Working memory
  • Self-Correction: Detects and fixes skill guidance errors
  • Self-Validation: Periodically verifies skill accuracy
  • Hooks Integration: Auto-triggers on skill events (before_start, after_complete, on_error)
  • Evolution Markers: Traceable changes with source attribution

Research-Based Design

Based on 2025 research:

Research Key Insight Application
SimpleMem Efficient lifelong memory Pattern accumulation system
Multi-Memory Survey Semantic + Episodic memory World knowledge + experiences
Lifelong Learning Continuous task stream learning Learn from every skill use
Evo-Memory Test-time lifelong learning Real-time adaptation

The Self-Improvement Loop

┌─────────────────────────────────────────────────────────────────┐
│                    UNIVERSAL SELF-IMPROVEMENT                    │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│   Skill Event → Extract Experience → Abstract Pattern → Update  │
│        │                  │                │         │          │
│        ▼                  ▼                ▼         ▼          │
│   ┌─────────────────────────────────────────────────────┐       │
│   │              MULTI-MEMORY SYSTEM                      │       │
│   ├─────────────────────────────────────────────────────┤       │
│   │  Semantic Memory   │  Episodic Memory  │ Working Memory │  │
│   │  (Patterns/Rules)  │  (Experiences)    │  (Current)     │  │
│   │  memory/semantic/  │  memory/episodic/ │  memory/working/│  │
│   └─────────────────────────────────────────────────────┘       │
│                                                                 │
│   ┌─────────────────────────────────────────────────────┐       │
│   │              FEEDBACK LOOP                            │       │
│   │  User Feedback → Confidence Update → Pattern Adapt   │       │
│   └─────────────────────────────────────────────────────┘       │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 409 lines

Files

What ships with it

9 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.

  1. 13d ago First seen · 409 lines · 53 tokens per session scan B ed0d4a70e034

Subscribe to this mod's changes

self-improving-agent is a skill published in the GitHub repository 1mancompany/OneManCompany (414 stars, last pushed 17d ago), licensed Apache-2.0. It adds 53 tokens to every session and 3,184 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

migrate-memory

Migrate legacy NanoClaw and Claude-native memory into the shared memory tree and provider-neutral standing instructions. Run after an update reports the shared-memory breaking change, or when a group still has .seed.md, legacy CLAUDE.md/CLAUDE.local.md, Claude auto-memory, or an unindexed imported-agent-memory.md.…

nanocoai/nanoclaw · 92 tokens

add-karpathy-llm-wiki

Add a persistent wiki knowledge base to a NanoClaw group. Based on Karpathy's LLM Wiki pattern. Triggers on "add wiki", "wiki", "knowledge base", "llm wiki", "karpathy wiki".

nanocoai/nanoclaw · 56 tokens

memory

Search past conversations in the agent's history log.

HKUDS/nanobot · 12 tokens

memory-to-skill

Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…

zilliztech/memsearch · 82 tokens

zylos-memory

Core memory system. Maintains persistent memory across sessions via tiered markdown files following the Inside Out model. Handles Memory Sync (processing conversations into structured memory), session rotation, consolidation, and context-aware state saving. Must be launched via a runtime-appropriate background…

zylos-ai/zylos-core · 68 tokens

autocontext-consumer

Use when an agent needs to USE knowledge Autocontext already produced - find which scenarios have knowledge, read the playbook and lessons for one, understand the on-disk file and folder layout, and move knowledge between checkouts. Host-agnostic; requires only the autoctx CLI and the filesystem.

greyhaven-ai/autocontext · 67 tokens