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 agentmods add commands/sugar-coffee/stokowski/releasegit clone --depth 1 https://github.com/Sugar-Coffee/stokowskiWrote 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/commands/sugar-coffee/stokowski/release)<a href="https://agentmods.dev/commands/sugar-coffee/stokowski/release"><img src="https://agentmods.dev/badge/commands/sugar-coffee/stokowski/release.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01312 |
| Opus 5 | $0.00000 | $0.00656 |
| Sonnet 5 | $0.00000 | $0.00262 |
| Haiku 4.5 | $0.00000 | $0.00131 |
Grade A, and why
release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are preparing a new release of Stokowski. Follow these steps exactly and interactively — confirm with the user before making any commits or opening PRs.
Step 1: Safety checks
Run the following checks and abort if either fails:
# Check we're on main
BRANCH=$(git branch --show-current)
if [ "$BRANCH" != "main" ]; then
echo "ERROR: Not on main branch (currently on '$BRANCH'). Switch to main before releasing."
exit 1
fi
# Check main is up to date with origin
git fetch origin main
LOCAL=$(git rev-parse HEAD)
REMOTE=$(git rev-parse origin/main)
if [ "$LOCAL" != "$REMOTE" ]; then
echo "ERROR: main is not up to date with origin/main. Pull or push first."
exit 1
fi
echo "✓ On main and up to date with origin"
If either check fails, stop immediately and tell the user what to fix.
Step 2: Find the baseline
# Get the latest tag, or the first commit if no tags exist
LAST_TAG=$(git describe --tags --abbrev=0 2>/dev/null || git rev-list --max-parents=0 HEAD)
echo "Last release: $LAST_TAG"
Step 3: Collect commits since last release
git log ${LAST_TAG}..HEAD --pretty=format:"%h %s" --no-merges
Review the commits and group them mentally by type:
feat:— new features (→ minor bump)fix:— bug fixes (→ patch bump)feat!:or body containingBREAKING CHANGE— breaking changes (→ major bump)docs:,chore:,ci:,refactor:— maintenance (→ patch bump if no feat/fix)
Step 4: Propose the semver bump
Get the current version:
grep '^version' pyproject.toml
Apply these rules:
- Any
feat!:orBREAKING CHANGE→ major bump - Any
feat:(no breaking changes) → minor bump - Only
fix:,chore:,docs:,ci:→ patch bump
Tell the user: "Based on the commits, I propose a [major/minor/patch] bump: vX.Y.Z → vA.B.C. Does this look right, or would you like a different version?"
Wait for the user to confirm or specify a different version before continuing.
Step 5: Write the release notes
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.
- 4d ago First seen · 147 lines · 0 tokens per session scan A 27bf0823e49c
release is a command published in the GitHub repository Sugar-Coffee/stokowski (114 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,312 tokens. 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.
Other commands, from other repositories
changelog
Generate a new changelog entry by reading all changeset files and creating a properly formatted entry in .changelog/v3.mdx.
merge-and-status
Merge the current PR, pull main, surface any open contributor PRs and untriaged contributor issues, and show open milestone issues.
ship
Deliver the increment. Then go live with a rollback you have run.
update-changelog-and-tag
You are preparing a release. Follow these steps precisely.
release-tag
Create and push a version tag after a release PR has been merged.
release
Orchestrate a complete release workflow with quality gates, version bumping, and publishing automation.