agent-self-improvement

agent-self-improvement is a skill for Claude Code from oyi77/1ai-skills. It costs 47 tokens per session (4,334 once invoked), scanned A, original, MIT.

A monitoring system for an agent's collection of skills that tracks how often they are used, how often they succeed, and how long they take.

In plain words
What is it for?
It helps analyze error patterns, measure user satisfaction, test skill variants, and suggest improvements.
Why use it?
It helps reveal failing, slow, unused, redundant, or incorrectly triggered skills instead of relying on guesswork.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the 1ai-skills plugin — 209 skills, 4 commands shipped together

Good fit It helps analyze error patterns, measure user satisfaction, test skill variants, and suggest improvements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oyi77/1ai-skills/agent-self-improvement
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 oyi77/1ai-skills --skill agent-self-improvement
Clone the repo
git clone --depth 1 https://github.com/oyi77/1ai-skills

Made for: Claude Code.

Or install 1ai-skills, the plugin that ships this one along with the rest of its 209 skills, 4 commands.

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 agent-self-improvement

README.md
[![agentmods](https://agentmods.dev/badge/skills/oyi77/1ai-skills/agent-self-improvement/github.svg)](https://agentmods.dev/skills/oyi77/1ai-skills/agent-self-improvement)
Your own site
<a href="https://agentmods.dev/skills/oyi77/1ai-skills/agent-self-improvement"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/agent-self-improvement/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 agent-self-improvement

Your own site · 80×15
<a href="https://agentmods.dev/skills/oyi77/1ai-skills/agent-self-improvement"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/agent-self-improvement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,334 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.04334
Opus 5 $0.00023 $0.02167
Sonnet 5 $0.00009 $0.00867
Haiku 4.5 $0.00005 $0.00433

Measured 8d ago against content hash 7bba81a38624, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agent-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.

core/agent-self-improvement/SKILL.md · 551 lines

How it starts

The opening of the file, as written. The whole thing — 551 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

A meta-skill that monitors the performance of all other skills in the portfolio, identifies bottlenecks and failure patterns, suggests improvements, and optionally applies optimizations. This is the flywheel that makes every other skill better over time. Track usage metrics, error rates, execution times, and user satisfaction to continuously improve the skill library.

Required Tools

  • Metrics Storage: SQLite (.omc/metrics.db) or JSON logs (.omc/logs/skill-metrics.jsonl)
  • Analysis: Python with pandas for data analysis
  • Git: For tracking skill changes and A/B testing variants
  • OMC State: .omc/state/ for skill execution tracking
  • Session Logs: .omc/sessions/ for historical performance data
  • Python 3.10+ with pandas, sqlite3

Capabilities

  • Track skill usage frequency, success rate, and execution time
  • Identify skills with high error rates or poor user satisfaction
  • Detect unused or redundant skills in the portfolio
  • Generate improvement proposals based on failure patterns
  • A/B test skill variants to measure improvement impact
  • Monitor skill trigger accuracy (false positives/negatives)
  • Track cross-skill dependencies and bottlenecks
  • Generate weekly/monthly skill portfolio health reports

When to Use

Trigger phrases:

  • "agent self improvement"

  • "Weekly maintenance routine for skill portfolio"

  • "After adding new skills, check portfolio balance"

  • "When a skill's error rate exceeds threshold (>10%)"

  • Weekly maintenance routine for skill portfolio

  • After adding new skills, check portfolio balance

  • When a skill's error rate exceeds threshold (>10%)

  • Before major skill updates, baseline current performance

  • When planning which skills to add/improve/remove

  • After user complaints about skill quality

When NOT to Use

  • Task is outside your authorization scope
  • You need to implement controls (use implementing-* skills)
  • Task is about analysis, not action (use analyzing-* skills)
  • You don't have access to target systems
  • Task requires compliance expertise (consult professionals)
  • Task is about defense, not offense (use defensive skills)

Read the full file on GitHub · 551 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 · 551 lines · 47 tokens per session scan A 7bba81a38624

Subscribe to this mod's changes

agent-self-improvement is a skill published in the GitHub repository oyi77/1ai-skills (12 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 4,334 once invoked, about $0.0002 per session on Opus 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 2026-09-03.

Related

Other skills, from other repositories

letter-hooker

Erweitert automation-self-care um Letter Hooks, Preflight-Bootloader, Dokument-Traversierungsregeln und selbstheilende Prompt-Kontext- Anreicherung für KI-Agenten und CLIs ohne native, ereignisgetriebene JSON-Lifecycle-Hooks (wie Antigravity / Gemini CLI). Nutzen, wenn ein Agent Preflight-Regeln injizieren, vor…

ellmos-ai/skills · 129 tokens

persistent-notes

Save notes locally to /mnt/workspace/notes.json file. Use when user wants to "save a note" or "remember something".

awslabs/agentcore-samples · 32 tokens

hive.context-preservation

Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.

aden-hive/hive · 24 tokens

hive.note-taking

Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.

aden-hive/hive · 30 tokens

capability-evolver

Self-evolution workflow for the agent. Before substantive work, recall past outcomes from evolution memory; while editing, detect improvement signals; at task end, record the outcome; when reusable, distill or search the EvoMap network for proven genes/capsules. Use when the user starts non-trivial work (a feature, a…

Dianel555/DSkills · 98 tokens

obsidian

Use the official Obsidian CLI (v1.12+) to manage vaults, notes, daily notes, search, tasks, tags, properties, links, templates, sync, publish, and workspaces. Use when the user mentions Obsidian, vaults, notes, or wants to automate note-taking and knowledge base workflows.

lvndry/jazz · 71 tokens