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.
npx skills add V-Songbird/foundry --skill cut-releasegit clone --depth 1 https://github.com/V-Songbird/foundryWrote 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.
[](https://agentmods.dev/skills/v-songbird/foundry/cut-release)<a href="https://agentmods.dev/skills/v-songbird/foundry/cut-release"><img src="https://agentmods.dev/badge/skills/v-songbird/foundry/cut-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.
<a href="https://agentmods.dev/skills/v-songbird/foundry/cut-release"><img src="https://agentmods.dev/badge/skills/v-songbird/foundry/cut-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00039 | $0.00962 |
| Opus 5 | $0.00019 | $0.00481 |
| Sonnet 5 | $0.00008 | $0.00192 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
cut-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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release a Foundry plugin edition
Use this workflow only for an explicit release request. Establish the plugin, edition and intended version from that request and the current repository state. If the edition is ambiguous, resolve it before writing metadata. Running in a particular assistant does not by itself choose the edition being released.
Sources of truth
| Edition | Plugin metadata | Catalog | Version owner |
|---|---|---|---|
| Claude | <plugin>/.claude-plugin/plugin.json on Claude |
.claude-plugin/marketplace.json in Foundry |
the Claude catalog entry |
| Codex | <plugin>/.codex-plugin/plugin.json on Codex |
.agents/plugins/marketplace.json in Foundry |
the native plugin manifest |
Both catalog entries identify the plugin repository, platform ref and full validated commit SHA. Claude's version and source.sha move together. A Codex release updates its native version and then pins that exact integrated commit; do not introduce a Claude-style version field into the Codex catalog.
Hush/Codex is not installable until its package and validation exist. Do not create a release or add it to the catalog merely because the branch exists.
Prepare a reviewable release
- Locate Foundry and the intended plugin checkout. Check its branch, HEAD,
working tree and published refs. Confirm its physical working directory with
git rev-parse --show-toplevel; worktree-list output alone can identify a submodule's gitdir instead. Preserve other working copies and unrelated edits. - Work on an appropriate non-main branch. On Windows, an existing Codex ref can prevent a codex/ prefix; use a non-conflicting maintenance branch. A plugin's main branch is its selector, never the implementation release destination.
- Establish the exact release surface and inspect the changes since the last published pin for this edition. A dirty checkout is not authorization to include everything in it. Prepare the requested files and checks before requesting any genuinely missing publication approval.
- Write a short user-facing CHANGELOG entry and update the edition's version owner. Use the user's version when supplied; otherwise choose or clarify the bump according to the actual compatibility change. Keep unrelated metadata.
- Use coordinate-readmes and check the actual candidate pair. The CLI supports
--pair <Claude-README> <Codex-README>and--git-pair <plugin-repo> <Claude-candidate-ref> <Codex-candidate-ref>. Shared changes need both candidates; model-specific measurements must retain their own evidence. Missing benchmarks stay explicitly unmeasured. - Run the relevant plugin, packaging, documentation and maintenance checks. Read the edition's compatibility/validation guide. Do not run a Claude hook canary against a Codex package, invent hook events, or treat unit tests as installed activation. Paid benchmarks and installations need their own scope.
What ships with it
1 file 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.
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.
- today First seen · 81 lines · 39 tokens per session scan A 1a900331291e
cut-release is a skill published in the GitHub repository V-Songbird/foundry (4 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 962 once invoked, about $0.0002 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 2026-09-10.
Other skills, from other repositories
release
This skill should be used when the user wants to create a new release — bump version, tag, push, create GitHub release, and optionally publish to npm. Use when user says "release", "bump version", "publish", "cut a release", or "release candidate".
changelog-summarizing
Use this skill when the user asks to summarize, recap, or post about repository changes in the Shopware AI Coding Tools marketplace since a given date — phrases like "write a changelog post for Discord", "recap this week's commits for Slack", "summarize what shipped since 2026-04-01", "draft a release announcement".…
plugin-updating
Use this skill when the user asks to bump, update, or release a new version of a plugin in the Shopware AI Coding Tools marketplace — phrases like "bump test-writing to 3.8.0", "release a patch for dev-tooling", "update the plugin version". Handles synchronized version bumps across plugin.json and every SKILL.md…
changelog
Ingest Claude Code changelog entries and integrate them into the current repo. Fetch (read-only display), diff (impact analysis, no edits), status (applied versions), and apply (full integrate pipeline, explicit user intent only). Use when: 'new cc version', 'what changed in claude code', 'apply changelog', a new CC…
release-info-writing
Use this skill when the user is completing features, deprecations, or breaking changes in the Shopware core repository that affect external developers, or when they ask to write release info, upgrade entries, release notes, release documentation, or changelog entries — phrases like "write a release info entry for my…
git-advanced
Use when performing complex git operations -- rebasing, cherry-picking, resolving merge conflicts, bisecting bugs, managing stashes, cleaning history, or working with monorepos. Goes beyond basic commit/push/pull.