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 | $0.00043 | $0.00547 |
| Opus 5.5 | $0.00017 | $0.00219 |
| Sonnet 5.5 | $0.00009 | $0.00109 |
| Haiku 4.5 | $0.00004 | $0.00055 |
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 2d 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.
What it actually says
cut-release
This is the Codex and Antigravity entrypoint for this repository's release
procedure. Use it only when explicitly invoked, as $cut-release in Codex or
/cut-release in Antigravity; take the plugin and requested version from the
user's message. Codex reads the invocation policy from agents/openai.yaml, and
Antigravity from disable-model-invocation above.
Before taking release actions, read and follow the complete canonical release procedure. The procedure is shared with Claude Code; do not duplicate its steps here.
Codex and Antigravity execution notes
- Resolve the canonical link relative to this skill directory. If it is missing, stop and report the missing procedure rather than inventing a release workflow.
- The canonical file's Claude-only frontmatter describes its discovery on that
host; its release steps apply here. Interpret
ReadandEditas the available file-reading and patch tools, not required tool names. - Run commands from the Foundry root, except step 4's pin check, which runs from
the checkout that holds the release commit and takes the root's path. On
Windows, use
rginstead of thegrepexample.claude plugin validateand step 5's Claude Code check need the Claude Code CLI, step 5's Codex check the codex CLI, andagy plugin validateand step 5's Antigravity check the Antigravity CLI; when one is absent, report that check as not run instead of skipping it silently. - Preserve existing authorization. Before each commit or push, verify the user's release request authorizes that action and its scope, and review the staged diff and the branch to be pushed so unrelated work cannot be included silently. Preparing or porting this skill does not authorize a release.
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.
- 2d ago Changed · +3 lines · +2 tokens per session 4f4219316bec
- 1mo ago Changed · +2 lines 8b05c7ca6d99
- 1mo ago Changed · -61 lines · +2 tokens per session fd7f2acd2d59
- 1mo ago Changed · +16 lines ca16075e5b96
- 1mo ago 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 2d ago), licensed MIT. It adds 43 tokens to every session and 547 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 2026-09-10.
cut-release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cut-releaseV-Songbird/foundry | Skill | 4 | 2d ago | MIT | A | 43 | Claude Code, Codex |
| changelog-summarizingshopwareLabs/ai-coding-tools | Skill | 45 | 10d ago | MIT | A | 106 | Claude Code |
| plugin-updatingshopwareLabs/ai-coding-tools | Skill | 45 | 10d ago | MIT | A | 102 | Claude Code |
| release-info-writingshopwareLabs/ai-coding-tools | Skill | 45 | 10d ago | MIT | A | 154 | Claude Code |
| releaseNikiforovAll/claude-code-marketplace | Skill | 2 | 5d ago | MIT | A | 63 | Claude Code |
| releasetomoking2004/claude-plugins | Skill | 3 | today | MIT | A | 142 | Claude Code |
| flow-next-landgmickel/flow-next | Skill | 718 | today | MIT | A | 35 | Claude Code, Codex |