agentmods.dev

agent_data_duckdb: Skill for Claude Code

.claude/skills/create-upstream-release/SKILL.md

create-upstream-release is a skill for Claude Code from axsaucedo/agent_data_duckdb. It costs 52 tokens per session (389 once invoked), scanned A, original, MIT.

A release workflow for opening a pull request that publishes a validated agent_data release to DuckDB's community extensions repository, then closing its tracking issue.

In plain words
What is it for?
Use it when a DuckDB release issue asks to publish agentdata: update main, read the target version, check for an existing pull request, prepare and open the upstream PR, and link it from the issue.
Why use it?
It checks the repository state and existing pull requests before publishing, reducing the chance of releasing the wrong commit or duplicating work.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is axsaucedo/agent_data_duckdb's own configuration. It tells Claude Code how to work on agent_data_duckdb itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent_data_duckdb configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is GH_TOKEN=$(gh auth token --user axsaucedo) python3 scripts/prepare_community_extension_pr.py --open-pr \.

not rated 31repo 18d ago A scan 52 tokens original MIT
View source ↗ axsaucedo/agent_data_duckdb
Reuse

Borrowing it

Nothing to install: this file belongs to axsaucedo/agent_data_duckdb. 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/axsaucedo/agent_data_duckdb/main/.claude/skills/create-upstream-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/axsaucedo/agent_data_duckdb

Made for: Claude Code.

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 create-upstream-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/axsaucedo/agent_data_duckdb/create-upstream-release/github.svg)](https://agentmods.dev/skills/axsaucedo/agent_data_duckdb/create-upstream-release)
Your own site
<a href="https://agentmods.dev/skills/axsaucedo/agent_data_duckdb/create-upstream-release"><img src="https://agentmods.dev/badge/skills/axsaucedo/agent_data_duckdb/create-upstream-release/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 create-upstream-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/axsaucedo/agent_data_duckdb/create-upstream-release"><img src="https://agentmods.dev/badge/skills/axsaucedo/agent_data_duckdb/create-upstream-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 389 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 $0.00052 $0.00389
Opus 5.5 $0.00021 $0.00156
Sonnet 5.5 $0.00010 $0.00078
Haiku 4.5 $0.00005 $0.00039

Measured 2mo ago against content hash b35d5fbaf2d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-upstream-release 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 2mo 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.

.claude/skills/create-upstream-release/SKILL.md · 22 lines

What it actually says

Publish the current main commit of agent_data to duckdb/community-extensions.

  1. Ensure you are on an up-to-date main with a clean tree: git checkout main && git pull. Read the target version from duckdb-release.toml and set REF=$(git rev-parse HEAD).

  2. Sanity-check there is no already-open upstream PR for this ref: gh pr list -R duckdb/community-extensions --author axsaucedo --state open. If one exists, report it and stop.

  3. Sync the fork and open the PR (use the personal account token, as the active gh account may be the work one):

    GH_TOKEN=$(gh auth token --user axsaucedo) gh repo sync axsaucedo/community-extensions --source duckdb/community-extensions
GH_TOKEN=$(gh auth token --user axsaucedo) python3 scripts/prepare_community_extension_pr.py --open-pr \
  --branch "bump-agent-data-${REF:0:12}" \
  --source-pr-url "https://github.com/axsaucedo/agent_data_duckdb/commit/${REF}"

    If a merged release PR exists for this ref, pass its URL as --source-pr-url instead of the commit URL.

  4. Find the open tracking issue (gh issue list --search "Publish agent_data in:title") and close it with a comment linking the upstream PR just opened.

  5. Report the upstream PR URL to the user. Merging is done by DuckDB maintainers; nothing further to do here.

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. 2mo ago First seen · 22 lines · 52 tokens per session scan A b35d5fbaf2d0

Subscribe to this mod's changes

create-upstream-release is a skill published in the GitHub repository axsaucedo/agent_data_duckdb (31 stars, last pushed 18d ago), licensed MIT. It adds 52 tokens to every session and 389 once invoked, about $0.0002 per session on Opus 5.5. 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.

Git and workflowReleases
Related

create-upstream-release compared with skills from other repositories

create-upstream-release next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
create-upstream-releaseaxsaucedo/agent_data_duckdbSkill3118d agoMITA52Claude Code
release-announcementpaperclipai/paperclipSkill111kyesterdayMITA42Claude Code, Codex
releasethedotmack/claude-memSkill114kyesterdayApache-2.0A13Claude Code
release-notesphuryn/pm-skillsSkill28k8d agoMITA57Claude Code
multi-agent-release-managerchromium/chromiumSkill25kyesterdayBSD-3-ClauseA27Claude Code, Codex
pack-submitaeonfun/aeonSkill788yesterdayMITA27Claude Code, Codex
updater_guidesiddsachar/row-botSkill1.7ktodayApache-2.0A22Claude Code, Codex