Borrowing it
Nothing to install: this file belongs to tenstorrent/tt-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tenstorrent/tt-studio/main/.claude/skills/cut-release/SKILL.mdgit clone --depth 1 https://github.com/tenstorrent/tt-studioWrote 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/tenstorrent/tt-studio/cut-release)<a href="https://agentmods.dev/skills/tenstorrent/tt-studio/cut-release"><img src="https://agentmods.dev/badge/skills/tenstorrent/tt-studio/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/tenstorrent/tt-studio/cut-release"><img src="https://agentmods.dev/badge/skills/tenstorrent/tt-studio/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 | $0.00144 | $0.01212 |
| Opus 5.5 | $0.00058 | $0.00485 |
| Sonnet 5.5 | $0.00029 | $0.00242 |
| Haiku 4.5 | $0.00014 | $0.00121 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cut a TT-Studio release
The release model (CONTRIBUTING → Release Process): an rc-vX.Y.Z branch is cut
from main, validated changes are cherry-picked from dev, the Rc vX.Y.Z PR is
squash-merged back into main after ≥2 approvals, and the merge commit is tagged
vX.Y.Z — the tag push is what builds and publishes the GHCR images. Git tags are
the only version source of truth.
The three python run.py flags automate the mechanical parts. All of them are
interactive, verify state before acting, and stop with a fix-it panel when
something is off — prefer them over hand-rolled git/gh sequences.
0. Preflight
- These flags need the GitHub CLI:
gh auth statusmust pass with push access. - The flags never switch your checkout (the RC is created with plumbing and
cherry-picked in a scratch worktree), so run them from any branch — including
a dirty one. Stay on a branch that has the flags;
maindoesn't until this tooling ships. - Figure out which stage the user is at and jump to it:
- no RC branch yet → Cut
- RC exists, fixes landed on dev → Stabilize
- RC approved and green → Ship
1. Cut
python run.py --make-rc-branch # asks: bump major / minor / patch
python run.py --make-rc-branch minor # or say it up front (also accepts vX.Y.Z)
Detects the latest release across tags, rc-v* branches, and Rc vX.Y.Z (#N)
merge commits on main (they have drifted historically), cuts rc-vX.Y.Z from
origin/main, pushes it, and opens the Rc vX.Y.Z PR against main with the
release test-plan checklist. Relay the PR URL to the user. One release at a
time: while an untagged rc-v* branch exists on origin, the cut refuses and
points at --update-rc-branch / --merge-rc-branch (or closing the stray RC).
2. Notes
Draft the release notes with the draft-release-notes skill (it owns the house style — do not restate its rules here). After the user approves the draft, put it at the top of the RC PR description, keeping the test-plan checklist below:
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.
- 1mo ago First seen · 102 lines · 144 tokens per session scan A 3538e18ce3e9
cut-release is a skill published in the GitHub repository tenstorrent/tt-studio (52 stars, last pushed yesterday), licensed Apache-2.0. It adds 144 tokens to every session and 1,212 once invoked, about $0.0006 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 2026-09-29.
cut-release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cut-releasetenstorrent/tt-studio | Skill | 52 | yesterday | Apache-2.0 | A | 144 | Claude Code |
| git-safetytamagui/tamagui | Skill | 14k | today | MIT | A | 0 | Claude Code |
| release-safetytamagui/tamagui | Skill | 14k | today | MIT | A | 0 | Claude Code |
| changesetfrappe/frappe-ui | Skill | 1.1k | 2d ago | MIT | A | 45 | Claude Code |
| publish-notesHoangNguyen0403/agent-skills-standard | Skill | 583 | yesterday | MIT | A | 20 | Codex |
| deploy-akashickachofugetsu09/akashic-agent | Skill | 518 | yesterday | MIT | A | 38 | Claude Code, Codex |
| git-workflowjezweb/claude-skills | Skill | 1.1k | 28d ago | MIT | A | 52 | Claude Code |