mcp-server-trello: Skill for Claude Code

.agents/skills/mcp-server-trello-release/SKILL.md

mcp-server-trello-release is a skill for Claude Code, Codex from delorenj/mcp-server-trello. It costs 183 tokens per session (3,816 once invoked), scanned A, original, MIT.

A release procedure for the @delorenj/mcp-server-trello repository. MCP is a standard way for an AI tool to connect to external services, and this server connects that workflow with Trello.

In plain words
What is it for?
Use it when bumping the version, preparing a release pull request, creating a tag, or publishing the server to npm and the MCP registry.
Why use it?
It prevents the npm package, MCP registry entry, server code, and changelog from reporting different versions or being published with the wrong release process.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is delorenj/mcp-server-trello's own configuration. It tells Claude Code and Codex how to work on mcp-server-trello 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 mcp-server-trello configures →

Reuse

Borrowing it

Nothing to install: this file belongs to delorenj/mcp-server-trello. 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/delorenj/mcp-server-trello/main/.agents/skills/mcp-server-trello-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/delorenj/mcp-server-trello

Made for: Claude Code, 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 mcp-server-trello-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/delorenj/mcp-server-trello/mcp-server-trello-release/github.svg)](https://agentmods.dev/skills/delorenj/mcp-server-trello/mcp-server-trello-release)
Your own site
<a href="https://agentmods.dev/skills/delorenj/mcp-server-trello/mcp-server-trello-release"><img src="https://agentmods.dev/badge/skills/delorenj/mcp-server-trello/mcp-server-trello-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.

agentmods 80×15 button for mcp-server-trello-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/delorenj/mcp-server-trello/mcp-server-trello-release"><img src="https://agentmods.dev/badge/skills/delorenj/mcp-server-trello/mcp-server-trello-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 183 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,816 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00183 $0.03816
Opus 5 $0.00092 $0.01908
Sonnet 5 $0.00037 $0.00763
Haiku 4.5 $0.00018 $0.00382

Measured 12d ago against content hash 3bd334f22b02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-server-trello-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 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/parity-check.sh, scripts/set-version.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/mcp-server-trello-release/SKILL.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-server-trello-release

The release rules for @delorenj/mcp-server-trello. This repo publishes to two registries off automation triggered by a PR merge — so a release is not "run publish", it is "get main correct and merge the PR". Get the version parity or the trigger semantics wrong and you desync npm from the MCP registry, or ship a server that lies about its own version.

Every fact below was VERIFIED on 2026-07-16 against this repo. The maintainer pivots fast — re-check the workflow files and versionbump.js before leaning on any of it. llr is the recency compass.


The one thing that breaks every time: version parity

There are four version literals in this repo, not one, plus the changelog. They must all read the same X.Y.Z before you open the release PR:

# Location Field Why it matters
1 package.json version Drives the npm publish.
2 server.json version (top level) Drives the MCP registry publish.
3 server.json packages[0].version Registry cross-checks it against #2 and the npm tarball.
4 src/index.ts new McpServer({ version }) (~line 44) What the server reports over MCP. If stale, tools/list clients see the wrong version.
5 CHANGELOG.md newest ## [X.Y.Z] - DATE heading Human record + release-notes source.

The trap: bun run versionbump:{patch,minor,major} (scripts/versionbump.js) only edits #1. It silently leaves #2, #3, #4 behind. That is exactly how server.json drifted to 1.5.6 while npm was on 1.7.1, and how the McpServer literal sat at 1.7.1 into a 1.8.0 cut. Never trust versionbump alone.

Use the bundled helper instead — it sets all four literals at once and flips the changelog heading:

.agents/skills/mcp-server-trello-release/scripts/set-version.sh 1.8.0

Then always confirm parity before committing:

.agents/skills/mcp-server-trello-release/scripts/parity-check.sh

Read the full file on GitHub · 269 lines

Files

What ships with it

3 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.

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. 12d ago First seen · 269 lines · 183 tokens per session scan A 3bd334f22b02

Subscribe to this mod's changes

mcp-server-trello-release is a skill published in the GitHub repository delorenj/mcp-server-trello (438 stars, last pushed 14d ago), licensed MIT. It adds 183 tokens to every session and 3,816 once invoked, about $0.0009 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 2026-08-30.