mcp-contrast: Skill for Claude Code

.claude/skills/update-changelog/SKILL.md

update-changelog is a skill for Claude Code from Contrast-Security-OSS/mcp-contrast. It costs 115 tokens per session (2,521 once invoked), scanned A, original, Apache-2.0.

A pre-release workflow for updating the Unreleased section of a changelog. A changelog is the file that records user-facing changes between software releases.

In plain words
What is it for?
Use it to compare changes since the last release, draft entries pull request by pull request, audit the draft, and return the approved text for the release process.
Why use it?
It helps ensure the next release documents all relevant merged changes without writing anything before a person approves the draft.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is Contrast-Security-OSS/mcp-contrast's own configuration. It tells Claude Code how to work on mcp-contrast 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-contrast configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Contrast-Security-OSS/mcp-contrast. 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/Contrast-Security-OSS/mcp-contrast/main/.claude/skills/update-changelog/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Contrast-Security-OSS/mcp-contrast

Made for: Claude Code.

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 update-changelog

README.md
[![agentmods](https://agentmods.dev/badge/skills/contrast-security-oss/mcp-contrast/update-changelog/github.svg)](https://agentmods.dev/skills/contrast-security-oss/mcp-contrast/update-changelog)
Your own site
<a href="https://agentmods.dev/skills/contrast-security-oss/mcp-contrast/update-changelog"><img src="https://agentmods.dev/badge/skills/contrast-security-oss/mcp-contrast/update-changelog/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 update-changelog

Your own site · 80×15
<a href="https://agentmods.dev/skills/contrast-security-oss/mcp-contrast/update-changelog"><img src="https://agentmods.dev/badge/skills/contrast-security-oss/mcp-contrast/update-changelog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,521 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 139
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 $0.00115 $0.02521
Opus 5 $0.00057 $0.01260
Sonnet 5 $0.00023 $0.00504
Haiku 4.5 $0.00012 $0.00252

Measured 12d ago against content hash 726e1e2d25ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

update-changelog 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.

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.

.claude/skills/update-changelog/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-release changelog update

Brings [Unreleased] in CHANGELOG.md up to date with every user-facing change merged since the last release tag, so the release ships with a finished changelog. The skill drafts, audits, and only then shows the human one final draft. Nothing is written to disk before the human approves.

When to run. Before triggering the Gradle Release workflow (see RELEASING.md), or when a human explicitly asks. Not part of routine feature development.

Usage

  • /update-changelog runs the full flow.
  • /update-changelog <guidance> passes free-text hints, e.g. /update-changelog the SBOM work is internal, skip it.
  • Deferred-landing mode, invoked by the /release skill: draft, audit, and get the human's approval as usual, but skip the branch question in Step 1, all of Step 6, and Step 7. The range is the base range only. Return the approved draft text and the suggested next version to the caller, which creates the release branch and lands the changelog itself.

Ground rules

  • Content goes into [Unreleased]. Never stamp a version heading for the upcoming release. Version selection belongs to the release workflow, not this skill.
  • Versions that already have a changelog section are settled. Never reopen, rewrite, or re-audit them.
  • Existing [Unreleased] entries may be amended or expanded when they are incomplete or wrong. Never delete one silently. Propose deletions in the draft and let the human decide.
  • Report a suggested next version (breaking changes → major, new capabilities → minor, otherwise patch). It is informational only. Do not act on it. Breaking here means removed or renamed tools, or changes to hosting requirements, a new Java version, a Spring Boot major, changed Docker or jar run instructions. Changes to the contrast-mcp-core library API are not breaking on their own, its only consumer is internal. Small tool contract changes (parameters, response shape) stay minor, AI consumers adapt.
  • Do not create beads. This is a one-file docs change.

Read the full file on GitHub · 205 lines

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 · 205 lines · 115 tokens per session scan A 726e1e2d25ec

Subscribe to this mod's changes

update-changelog is a skill published in the GitHub repository Contrast-Security-OSS/mcp-contrast (23 stars, last pushed today), licensed Apache-2.0. It adds 115 tokens to every session and 2,521 once invoked, about $0.0006 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.