self-improve

self-improve is a skill for Claude Code, Codex from strikersam/autonomous-ai-agency. It costs 0 tokens per session (407 once invoked), scanned A, original, MIT.

A process for reviewing an agent’s skill library to find outdated instructions, overlaps, and missing skills, then proposing or implementing improvements.

In plain words
What is it for?
Use it after difficult work, when existing skills do not fit well, or during periodic maintenance of the skill library.
Why use it?
It turns repeated problems and uncovered needs into clearer, reusable guidance for future tasks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it after difficult work, when existing skills do not fit well, or during periodic maintenance of the skill library.

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

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-improve

README.md
[![agentmods](https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/self-improve/github.svg)](https://agentmods.dev/skills/strikersam/autonomous-ai-agency/self-improve)
Your own site
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/self-improve"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/self-improve/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-improve

Your own site · 80×15
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/self-improve"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/self-improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 407 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 $0.00000 $0.00407
Opus 5 $0.00000 $0.00204
Sonnet 5 $0.00000 $0.00081
Haiku 4.5 $0.00000 $0.00041

Measured 11d ago against content hash 52888a73a546, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

self-improve 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 11d 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.

.agents/skills/self-improve/SKILL.md · 47 lines

What it actually says

Skill: Self-Improve

Purpose

Enables the agent to analyze its own skill library, identify gaps or weaknesses, and propose or implement improvements to existing skills or new skill definitions.

When to Use

  • After completing a complex task where no existing skill quite fit
  • When patterns emerge across multiple issues/tasks that aren't yet captured as skills
  • When a skill's instructions led to suboptimal results
  • Periodically as a meta-maintenance task

Process

1. Audit Existing Skills

  • Read all .agents/skills/*/SKILL.md files
  • Note skills that are vague, outdated, or missing key steps
  • Identify overlapping skills that could be merged

2. Identify Gaps

  • Review recent issue resolutions and pull requests
  • List patterns that recurred but lacked a matching skill
  • Consider what skills would have saved time or improved quality

3. Propose Improvements

  • For each gap or weakness, draft a new or updated SKILL.md
  • Follow the existing skill format (Purpose, When to Use, Process, Output, Notes)
  • Keep skills atomic and composable — one concern per skill

4. Implement

  • Write new skill files to .agents/skills/<skill-name>/SKILL.md
  • Update existing skills in place if improving them
  • Do not delete skills without a clear reason documented in the changelog

5. Validate

  • Confirm new skills follow repository conventions
  • Cross-reference new skills with existing ones to avoid duplication
  • Add changelog entry under [Unreleased]

Output

  • One or more new or updated .agents/skills/*/SKILL.md files
  • A changelog entry summarizing what was added or changed

Notes

  • Skills should be written for an AI agent audience, not human developers
  • Prefer explicit step-by-step instructions over abstract descriptions
  • When improving a skill, preserve its original intent unless the intent itself was wrong
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. 11d ago First seen · 47 lines · 0 tokens per session scan A 52888a73a546

Subscribe to this mod's changes

self-improve is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 407 tokens. 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

assimilate-popular-workflows

This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable…

a5c-ai/babysitter · 110 tokens

process-builder

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

a5c-ai/babysitter · 32 tokens

mcp-app-verification

Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.

a5c-ai/babysitter · 48 tokens

mcp-app-scaffolding

Scaffolds MCP App project structure with correct directory layout, dependencies, entry points, and framework-specific templates. Handles React (useApp hook), Vanilla JS, Vue, Svelte, Preact, and Solid.

a5c-ai/babysitter · 50 tokens

mcp-csp-investigation

Comprehensive Content Security Policy audit for MCP Apps in sandboxed iframes. Discovers all network origins, traces them to source, and generates CSP configuration for registerAppResource.

a5c-ai/babysitter · 43 tokens

frontmatter-parsing

YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.

a5c-ai/babysitter · 40 tokens