coding-tools-mcp: Skill for Codex

.agents/skills/build-portable/SKILL.md

build-portable is a skill for Codex from shelizi/coding-tools-mcp. It costs 50 tokens per session (486 once invoked), scanned A, original, Apache-2.0.

A repeatable build process for creating and checking a Windows portable ZIP release of Coding Tools MCP, a desktop application. It builds the app, packages the executable, and prints SHA-256 hashes for verification.

In plain words
What is it for?
Building a portable Windows release, incrementing the patch version for a new release, creating the versioned ZIP, troubleshooting localhost:1420 errors, and retrying failed builds.
Why use it?
It avoids packaging a development-mode executable that incorrectly tries to load the app from localhost. It also keeps release versions and extracted build folders consistent.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is shelizi/coding-tools-mcp's own configuration. It tells Codex how to work on coding-tools-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything coding-tools-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shelizi/coding-tools-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/shelizi/coding-tools-mcp/main/.agents/skills/build-portable/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/shelizi/coding-tools-mcp

Made for: Codex.

Wrote 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.

agentmods badge for build-portable

README.md
[![agentmods](https://agentmods.dev/badge/skills/shelizi/coding-tools-mcp/build-portable.svg)](https://agentmods.dev/skills/shelizi/coding-tools-mcp/build-portable)
Your own site
<a href="https://agentmods.dev/skills/shelizi/coding-tools-mcp/build-portable"><img src="https://agentmods.dev/badge/skills/shelizi/coding-tools-mcp/build-portable.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 486 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.00486
Opus 5 $0.00025 $0.00243
Sonnet 5 $0.00010 $0.00097
Haiku 4.5 $0.00005 $0.00049

Measured 7d ago against content hash 6a3c7b845e27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

build-portable 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 7d 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.

.agents/skills/build-portable/SKILL.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Portable

Run the deterministic project script from the repository root:

pnpm run desktop:portable

The script builds the frontend, builds the Tauri release with the required custom-protocol feature, copies the executable, creates the versioned ZIP, and prints SHA-256 hashes.

Portable ZIP filenames and ZIP top-level directories are versioned. The expanded latest-build directory is stable and versionless (dist-portable/Coding.Tools.MCP_x64_portable) so each successful build replaces it instead of accumulating extracted copies.

Guardrails

  • package.json is the single source of truth for the release version. For every new requested portable release build, run pnpm run version:patch exactly once before compiling. This updates the source version and synchronizes the package/Cargo metadata; src-tauri/tauri.conf.json reads the version directly from package.json. A retry of the same failed build only reruns pnpm run desktop:portable and does not increment again.
  • Never package an executable produced by bare cargo build --release. Without custom-protocol, Tauri treats the binary as development mode and navigates to http://localhost:1420.
  • Never copy an older executable after a build timeout or failure. Keep the existing package unchanged and report the build error.
  • If running Cargo manually for diagnosis, include --features custom-protocol.
  • Treat the release compile-time error in src-tauri/src/main.rs as intentional; use the portable script instead of bypassing it.
  • Build the ZIP from isolated staging. If the expanded portable executable is running and locked, accept the warning and deliver the newly generated ZIP; do not terminate the user's app implicitly.

Verify

After the script succeeds:

  • Confirm the stable expanded folder contains Coding Tools MCP.exe.
  • Confirm the versioned ZIP contains its versioned top-level folder and executable.
  • Report the ZIP path, byte size, and SHA-256 hash.
  • Launch the packaged executable when desktop interaction is available and confirm it renders embedded UI rather than localhost.

Read the full file on GitHub · 35 lines

Files

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.

Changes

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.

  1. 7d ago First seen · 35 lines · 50 tokens per session scan A 6a3c7b845e27

Subscribe to this mod's changes

build-portable is a skill published in the GitHub repository shelizi/coding-tools-mcp (0 stars, last pushed 15d ago), licensed Apache-2.0. It adds 50 tokens to every session and 486 once invoked, about $0.0003 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.