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/shelizi/coding-tools-mcp/node-agent-portable-packagernpx skills add shelizi/coding-tools-mcp --skill node-agent-portable-packagergit clone --depth 1 https://github.com/shelizi/coding-tools-mcpWrote 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/shelizi/coding-tools-mcp/node-agent-portable-packager)<a href="https://agentmods.dev/skills/shelizi/coding-tools-mcp/node-agent-portable-packager"><img src="https://agentmods.dev/badge/skills/shelizi/coding-tools-mcp/node-agent-portable-packager.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 5.1 | $0.00089 | $0.01009 |
| Opus 5 | $0.00044 | $0.00504 |
| Sonnet 5 | $0.00018 | $0.00202 |
| Haiku 4.5 | $0.00009 | $0.00101 |
Grade A, and why
node-agent-portable-packager 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 5d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Node Agent Portable Packager
Operate on the Coding Tools MCP repository that contains packages/node-agent.
Version model
Keep these sources independent:
- Read the Node Agent application version from
packages/node-agent/package.json#version. - Read the Portable wrapper version from
packages/node-agent/portable-version.json#version. - Read this Skill version from
VERSIONbeside this file. - Derive the release tag as
node-agent-v<agent>-portable-v<portable>; this tag is release provenance, not a fourth independent version.
Never synchronize or bulk-bump them. Increment only the component whose behavior changed. Read references/packaging-rules.md before changing version, edition, or archive policy.
Editions
bundled-node: includesruntime/node.exeandruntime/NODE-LICENSE.txt; must not require system Node.js or a package manager after extraction.system-node: excludes the runtime directory and Node.js license; requires Windows x64 Node.js 22 or later asnode.exeonPATH; must not require a package manager after extraction.
Both editions contain the same compiled application and production dependencies and use the same default per-user data directory.
Workflow
- Inspect Git status and preserve unrelated changes and generated artifacts.
- Review the changes being released and choose independent version increments.
- Run the normal Node Agent verification before creating the release identity.
- Commit all release source and version changes. Require a clean worktree after the commit.
- Create an annotated
node-agent-v<agent>-portable-v<portable>tag on that exact commit. - Run
scripts/check-release-versions.ps1 -RepositoryRoot <repo>from this Skill. Require the expected annotated tag to resolve toHEAD, a clean worktree, valid versions, and expected artifact names. - Run
pnpm run node-agent:portablefrom the repository root to build both editions from the tagged commit. Use the focused:bundledor:systemcommands only when explicitly requested. - Inspect both ZIP names and manifests; require Agent version, Portable version, edition, release tag, and full Git commit in each artifact identity.
- Confirm common application contents are present in both editions. Confirm only
bundled-nodecontainsruntime/node.exeand the Node license. - Extract both ZIPs to paths containing spaces. Start each with
start-node-agent.bat --no-browseron isolated ports and data directories, then verify/health,/ui, and static UI assets. - Stop both smoke-test processes cleanly, validate every checksum entry, and compute both archive SHA-256 values.
- Deliver both Portable ZIPs separately from the Skill ZIP.
What ships with it
4 files 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.
- 5d ago First seen · 69 lines · 0 tokens per session scan A a7640b3ae717
node-agent-portable-packager is a skill published in the GitHub repository shelizi/coding-tools-mcp (0 stars, last pushed 13d ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,009 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
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.
changelog
Create changelog files for important commits in a PR.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
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…