Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Self Rewriter

ASecurity

Use for Self-Rewriting Core: AST analyze, patch, commit.

5 stars
0 votes
0 copies
0 views
Added 10/4/2026
ai-agentspythonbashgit

Works with

cli

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add openamer/openamer --skill self-rewriter --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Self Rewriter?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Self Rewriter
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/openamer-self-rewriter/badge)](https://www.skillsdirectory.com/skills/openamer-self-rewriter)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: self-rewriter
description: "Use for Self-Rewriting Core: AST analyze, patch, commit."
author: OpenAmer
tags: [self-rewriting, core-evolution, ast, patching, auto-commit, cron]
trigger: "Use when: (a) the user asks to improve/analyze/fix the openamer_cli/ codebase, (b) the user asks to run the self-rewriter, (c) the cron job triggers the 6h scan cycle"
---

# Self-Rewriting Core Skill

Der Self-Rewriter ist ein autonomes Core-Evolution-Tool, das das `openamer_cli/` Verzeichnis
auf Ineffizienzen scannt, Patches generiert, validiert und automatisch committed.

## Standort

- **Script**: `C:\Users\damir\openamer-repo\scripts\self-rewriter.py`
- **Cron-Kopie**: `$OPENAMER_HOME\scripts\self-rewriter.py`
- **Arbeitsverzeichnis**: `.rewriter/` im Repository-Root
  - `pending/` — generierte Patches (unified diff)
  - `applied/` — angewandte Patches (Archiv)
  - `reports/latest.json` — letzter Scan-Report

## CLI-Usage

```bash
python scripts/self-rewriter.py --scan              # Core analysieren
python scripts/self-rewriter.py --suggest           # Verbesserungen anzeigen
python scripts/self-rewriter.py --patch             # Patches generieren (max 3)
python scripts/self-rewriter.py --apply             # Patches validieren + commiten + mergen
python scripts/self-rewriter.py --all               # Full Cycle (scan -> patch -> apply)
python scripts/self-rewriter.py --all --dry-run     # Full Cycle nur anzeigen
python scripts/self-rewriter.py --scan --max-patches 5
python scripts/self-rewriter.py --apply --yes       # Non-interactive apply
python scripts/self-rewriter.py --repo /pfad/zum/repo --scan
```

## Exit-Codes

| Code | Bedeutung |
|------|-----------|
| 0 | Nichts zu tun — alles sauber |
| 1 | Patches verfuegbar (issues gefunden) |
| 2 | Patches angewandt und committed |

## Was wird analysiert (AST-basiert)

1. **Doppelte Imports** — selbes Modul mehrfach importiert
2. **Zu lange Funktionen** — > 100 Zeilen
3. **Fehlende Type Hints** — Parameter/Rueckgabewert ohne Type Annotation
4. **Leere except-Bloecke** — `except: pass` (sicherheitsrelevant)
5. **TODO/FIXME-Kommentare** — markierte Stellen im Code

## Patches & Git-Workflow

1. Branch `rewriter-tmp` wird von `main` erstellt
2. Patches werden via `patch -p0` / `patch -p1` angewandt
3. `py_compile` validiert die Syntax
4. Bei Erfolg: Commit + Merge zurueck zu `main` (--no-ff)
5. Branch wird geloescht
6. Angewandte Patches wandern von `pending/` -> `applied/`

## Cron-Job (alle 6h)

Der Cron-Job `self-rewriter-scan` laeuft alle 360 Minuten (6h) und fuehrt
`self-rewriter.py --scan` aus. Er prueft ob neue Issues aufgetaucht sind
und postet nur bei Aenderungen einen Report.

## Troubleshooting

- **"Core-Verzeichnis nicht gefunden"**: Script sucht in `~/openamer-repo/` und Umgebung.
  Mit `--repo /absoluter/pfad` explizit angeben.
- **Patch-Apply schlaegt fehl**: Patches arbeiten gegen den aktuellen `main`-Branch.
  Bei Konflikten sind manuelle Eingriffe noetig — der rewriter-tmp Branch bleibt dann bestehen.
- **Report nicht gefunden**: `--suggest` und `--patch` brauchen einen vorherigen `--scan`-Report.

Attribution

openameropenamer
View sourceSee grades on GitHubMore from openamer →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →