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 skills/mazumba/opencode-dockerized/release-smoke-testnpx skills add mazumba/opencode-dockerized --skill release-smoke-testgit clone --depth 1 https://github.com/mazumba/opencode-dockerizedWhat 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 | $0.00060 | $0.01113 |
| Opus 5 | $0.00030 | $0.00557 |
| Sonnet 5 | $0.00012 | $0.00223 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade C, and why
release-smoke-test scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$SMOKE" This is a copy
100% identical to release-smoke-test — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Smoke Test
Use this skill to validate an oh-my-opencode-slim release candidate before
public npm publish. Test the packed artifact, not @latest and not the source
tree.
Core Workflow
- Start from the release-prep branch or commit.
- Build and pack the candidate.
- Install the tarball into a throwaway app.
- Create an isolated OpenCode config pointing at the installed
node_modules/oh-my-opencode-slim/dist/index.js. - Run
opencode debug configand verifyplugin_originscontains only the intended plugin when doing an isolation smoke. - Run non-pure
opencode run --print-logs --log-level DEBUG. - Search isolated logs for the original crash signature.
- Record exact artifact, model, OpenCode version, command shape, result, and limitations on the release issue or PR.
Pack Candidate
Use a temp directory so release validation never depends on the local package cache.
SMOKE=/tmp/oh-my-opencode-slim-release-smoke
rm -rf "$SMOKE"
mkdir -p "$SMOKE/pkg" "$SMOKE/app" "$SMOKE/home" "$SMOKE/xdg/opencode" "$SMOKE/run"
bun run build
npm pack --pack-destination "$SMOKE/pkg"
Install the tarball:
cd "$SMOKE/app"
bun init -y
bun add "$SMOKE/pkg"/oh-my-opencode-slim-*.tgz
node -p "require('./node_modules/oh-my-opencode-slim/package.json').version"
Isolated Config
Write the minimal OpenCode config:
cat > "$SMOKE/xdg/opencode/opencode.json" <<EOF
{
"model": "opencode/deepseek-v4-flash-free",
"plugin": [
"file://$SMOKE/app/node_modules/oh-my-opencode-slim/dist/index.js"
],
"agent": {
"orchestrator": {
"model": "opencode/deepseek-v4-flash-free"
}
}
}
EOF
Use env -i for the cleanest smoke. This strips host OPENCODE_*, ORCA_*,
and project overlay variables that can silently add plugins or provider aliases.
env -i PATH="$PATH" HOME="$SMOKE/home" XDG_CONFIG_HOME="$SMOKE/xdg" \
opencode debug config
Confirm:
plugin_originshas exactly one entry.- That entry points to the temp app's packed
dist/index.js. - The model is the one intended for the smoke.
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 First seen · 159 lines · 60 tokens per session scan C 3e6b3f1e03de
release-smoke-test is a skill published in the GitHub repository mazumba/opencode-dockerized (5 stars, last pushed 5d ago), licensed MIT. It adds 60 tokens to every session and 1,113 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). It is 100% identical to release-smoke-test, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
release
Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.
release-notes
Draft concise release notes.
greptimedb-release
Runbook for publishing a new GreptimeDB version (tag + GitHub release + docs release-note PR) on the upstream GreptimeTeam/greptimedb repo. Use when asked to "release" / "publish" a GreptimeDB version (e.g. v1.1.0, v1.0.3).
refresh-arm-sdk-release
WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…
store-update
在 CCX Desktop 发布后下载 Store MSIX 并生成发布公告。用户提到 Store 上架、MSIX、从 GitHub Release 下载 store.msix、发布后同步 Windows Store、从 release 填写商店更新内容时必须使用此技能。该技能会下载最新 GitHub Release 的 amd64/arm64 MSIX,校验 sha256,从 Release body 生成 Store listing releaseNotes 预览,并输出手动上传指引。.