codeberg-api

A skill for working with Codeberg and Forgejo, services for hosting Git repositories, through their REST API, a web interface for repository operations.

In plain words
What is it for?
Use it to read or edit files, manage issues, create pull requests, inspect branches, tags, commits, and releases, search repositories, and trigger CI/CD workflows.
Why use it?
It avoids manually performing common repository tasks and supports both Codeberg and self-hosted Forgejo installations.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/d-o-hub/github-template-ai-agents/codeberg-api
Any agent
npx skills add d-o-hub/github-template-ai-agents --skill codeberg-api
Clone the repo
git clone --depth 1 https://github.com/d-o-hub/github-template-ai-agents

Made for: Claude Code, Codex.

Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,665 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00107 $0.01665
Opus 5 $0.00053 $0.00833
Sonnet 5 $0.00021 $0.00333
Haiku 4.5 $0.00011 $0.00167

Measured 2d ago against content hash dc0ce833a331, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codeberg-api scanned grade A with 1 finding 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/forgejo_api.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Bash(python:*|curl:*) Read
.agents/skills/codeberg-api/SKILL.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forgejo/Codeberg API Skill

Automates Forgejo repository operations using the REST API (v1). Compatible with Codeberg and self-hosted Forgejo instances.

When to Use

Activate when you need to:

  • Read or write files in a Forgejo/Codeberg repository
  • Create/update/close issues or pull requests
  • List branches, tags, commits, or releases
  • Search repositories or users
  • Trigger CI/CD via repository dispatch
  • Automate any git-forge operation

Prerequisites

pip install httpx python-dotenv

Authentication

Set FORGEJO_TOKEN (or CODEBERG_TOKEN) in your environment or .env file. Generate at: Forgejo/Codeberg → Settings → Applications → Generate Token.

Required scopes per operation:

Operation Scope needed
Read public repos (none, token optional)
Read private repos read:repository
Write files / create PRs write:repository
Manage issues write:issue
Read user info read:user
export FORGEJO_TOKEN=your_token_here
# or place in .env at project root

Base URL Configuration

The skill defaults to Codeberg (https://codeberg.org/api/v1). For self-hosted Forgejo instances, set FORGEJO_BASE_URL:

export FORGEJO_BASE_URL=https://forgejo.example.com/api/v1

Base URL & Headers

Base URL : https://codeberg.org/api/v1 (default)
Auth     : Authorization: token <FORGEJO_TOKEN>
Content  : Content-Type: application/json

Commands

CLI Usage (from project root)

# List repos for a user
python .agents/skills/codeberg-api/scripts/forgejo_api.py repos --owner username

# Get file contents
python .agents/skills/codeberg-api/scripts/forgejo_api.py get-file \
  --owner username --repo myrepo \
  --path README.md --branch main

# Create an issue
python .agents/skills/codeberg-api/scripts/forgejo_api.py create-issue \
  --owner username --repo myrepo \
  --title "Bug: xyz" --body "Description"

# List open issues
python .agents/skills/codeberg-api/scripts/forgejo_api.py list-issues \
  --owner username --repo myrepo --state open

# Create or update a file
python .agents/skills/codeberg-api/scripts/forgejo_api.py put-file \
  --owner username --repo myrepo \
  --path docs/test.md --content "# Hello" \
  --message "docs: add test file" --branch main

Read the full file on GitHub · 231 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 231 lines · 107 tokens per session scan A dc0ce833a331

Subscribe to this mod's changes

codeberg-api is a skill published in the GitHub repository d-o-hub/github-template-ai-agents (2 stars, last pushed 2d ago), licensed MIT. It adds 107 tokens to every session and 1,665 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.