self-improving-agent

self-improving-agent is a skill for Claude Code, Codex from Tyuts/xiaobai-skills. It costs 68 tokens per session (654 once invoked), scanned A, original, MIT.

A project-local guide for improving Xiaobai Skills based on meaningful changes, user feedback, installation problems, or repeated workflow issues.

In plain words
What is it for?
Deciding whether to update project rules, user documentation, the roadmap, or promotion notes after a recurring problem or significant project change.
Why use it?
It prevents useful lessons from being lost while avoiding unnecessary updates after every small change.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Deciding whether to update project rules, user documentation, the roadmap, or promotion notes after a recurring problem or significant project change.

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

agentmods badge for self-improving-agent

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

agentmods 80×15 button for self-improving-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/tyuts/xiaobai-skills/self-improving-agent"><img src="https://agentmods.dev/badge/skills/tyuts/xiaobai-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 654 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 $0.00068 $0.00654
Opus 5 $0.00034 $0.00327
Sonnet 5 $0.00014 $0.00131
Haiku 4.5 $0.00007 $0.00065

Measured 9d ago against content hash d0f49adfaf54, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

skills/self-improving-agent/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-Improving Agent

This is a repo-local skill for Xiaobai Skills. It helps the project learn from real work without turning every task into expensive reflection.

Use it only when one of these happens:

  • A user reports an install or curation failure.
  • A promotion experiment teaches something reusable.
  • The recommended starter stack changes.
  • The agent repeatedly searches for the same repo knowledge.
  • A workflow repeats enough to deserve a repo-local skill.
  • A release reveals missing docs, checks, or restore steps.

Do not use it after every small edit.

Step 1: Diagnose The Learning

Ask:

  1. Did the repo structure or command flow change?
  2. Did the user correct a behavior that should persist?
  3. Did an install command fail in a way future agents should know?
  4. Did a starter-stack decision prove good or bad?
  5. Did a repeated workflow emerge?

If the answer is no, make no changes.

Step 2: Choose The Right Artifact

  • Update AGENTS.md for short repo rules, commands, gotchas, or decision history.
  • Update README.md for user-facing install or positioning changes.
  • Update ROADMAP.md for future work.
  • Update docs/promotion-kit.md for launch and marketing learnings.
  • Create skills/<name>/SKILL.md only for repeatable multi-step workflows.

Prefer one concise update over several files.

Step 3: Update AGENTS.md Safely

When editing AGENTS.md:

  • Keep entries short and repo-specific.
  • Add dated decision notes only when they explain future behavior.
  • Remove or revise stale notes instead of appending contradictions.
  • Keep the file readable for every future session.
  • Never add secrets, payment details, tokens, or private user data.

Step 4: Create Repo-Local Skills Sparingly

Create a new skill only when the workflow is:

  • repeated
  • multi-step
  • specific enough to benefit from written procedure
  • useful for future maintainers

Use:

skills/<skill-name>/SKILL.md

The skill must include:

  • clear name
  • clear description
  • trigger conditions
  • steps
  • output contract

Read the full file on GitHub · 96 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. 9d ago First seen · 96 lines · 68 tokens per session scan A d0f49adfaf54

Subscribe to this mod's changes

self-improving-agent is a skill published in the GitHub repository Tyuts/xiaobai-skills (59 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 654 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…

anthropics/claude-plugins-official · 82 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

gke-workload-security

Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…

google/skills · 181 tokens

gke-reliability

Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).

google/skills · 73 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

ast-grep

Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for…

JanDeDobbeleer/oh-my-posh · 80 tokens