What is self-improvement?

A review workflow for capturing lessons after a substantial coding session. It looks for recurring mistakes, useful patterns, missing project context, and repeatable workflows.

Use it after a feature, refactor, or other major work session to suggest updates to project notes, known pitfalls, skills, context files, or workflows.

It helps preserve knowledge that would otherwise be forgotten after the session. Proposed changes are shown for review instead of being added automatically.

How systemowiec/ai-agents-workspace-starter configures Claude Code and

Reuse

Borrowing it

Nothing to install: this file belongs to systemowiec/ai-agents-workspace-starter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/systemowiec/ai-agents-workspace-starter/main/.agents/skills/self-improvement/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/systemowiec/ai-agents-workspace-starter

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/systemowiec/ai-agents-workspace-starter/self-improvement/github.svg)](https://agentmods.dev/skills/systemowiec/ai-agents-workspace-starter/self-improvement)

Your own site

<a href="https://agentmods.dev/skills/systemowiec/ai-agents-workspace-starter/self-improvement"><img src="https://agentmods.dev/badge/skills/systemowiec/ai-agents-workspace-starter/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/systemowiec/ai-agents-workspace-starter/self-improvement"><img src="https://agentmods.dev/badge/skills/systemowiec/ai-agents-workspace-starter/self-improvement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 559 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.

Model	Per session	Once invoked
Fable 5.1	$0.00028	$0.00559
Opus 5	$0.00014	$0.00280
Sonnet 5	$0.00006	$0.00112
Haiku 4.5	$0.00003	$0.00056

Measured 10d ago against content hash 67baee065207, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 10d 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-improvement/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-Improvement - Progressive Learning

Overview

The agent analyzes work performed and proposes improvements to the project configuration. NEVER adds automatically - always presents proposals for review.

When to Use

After completing a major work session (new feature, refactor)
When the user runs /self-improvement
When the agent discovers a repeatable pattern or pitfall

When NOT to use:

During implementation (focus on the task)
For trivial changes (one file, small fix)

Process

1. Gather context

Read:

docs/specs/ - recent implementation reports
.agents/learnings/gotchas.md - current state of knowledge
Recent commits (git log -10 --oneline)
Changed files in recent commits

2. Identify possible improvements

Type	Goal	Where to save
Gotcha	Pitfall, unexpected behavior	`.agents/learnings/gotchas.md`
Pattern	Repeatable code pattern	`.agents/skills/<new-skill>/SKILL.md`
Context update	New model, endpoint, module	`.agents/context/*.md`
Workflow	Repeatable process	`.agents/workflows/<new>.md`

3. Format proposals

For each proposal provide:

### [Type]: [Short title]

**Context**: Where/when this occurs
**Problem**: What happened or what is repeatable
**Proposal**: What to add/change
**File**: [file path]

4. Present to the user

NEVER add automatically
Present the list of proposals
Wait for approval of each one separately
After approval - add to the appropriate files (in the same commit)

Gotcha Entry Template

### [short title]
**Context**: [where/when this occurs]
**Problem**: [what happened]
**Solution**: [how to fix it]
**Date**: [YYYY-MM-DD]

Pattern Proposal Template

### New skill proposal: [name]

**Observation**: [what is repeating]
**Example 1**: [where it occurred]
**Example 2**: [where it occurred]
**Proposed skill**: [short description]

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.

10d ago First seen · 88 lines · 28 tokens per session scan A 67baee065207

Subscribe to this mod's changes

self-improvement is a skill published in the GitHub repository systemowiec/ai-agents-workspace-starter (2 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 559 once invoked, about $0.0001 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 2026-08-31.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

ai-agents-workspace-starter: Skill for Claude Code