mcp-contrast: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from Contrast-Security-OSS/mcp-contrast. It costs 106 tokens per session (2,439 once invoked), scanned A, original, Apache-2.0.

A step-by-step release workflow for mcp-contrast, a software project that provides an MCP server. MCP is a way for AI agents to use external tools through a standard connection.

In plain words
What is it for?
Checking repository state, preparing the changelog, choosing a version, creating the release work, running tests, publishing release artifacts, updating notes, and announcing the release.
Why use it?
It keeps release tasks in the right order and requires human approval before publishing artifacts, which are built files or packages. It also supports continuing after an interrupted release.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

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/release/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 release

README.md
[![agentmods](https://agentmods.dev/badge/skills/contrast-security-oss/mcp-contrast/release.svg)](https://agentmods.dev/skills/contrast-security-oss/mcp-contrast/release)
Your own site
<a href="https://agentmods.dev/skills/contrast-security-oss/mcp-contrast/release"><img src="https://agentmods.dev/badge/skills/contrast-security-oss/mcp-contrast/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,439 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 Rogue Agent · line 178
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 $0.00106 $0.02439
Opus 5 $0.00053 $0.01220
Sonnet 5 $0.00021 $0.00488
Haiku 4.5 $0.00011 $0.00244

Measured 8d ago against content hash 88d6e9faf2fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

release scanned grade A 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. DockerHub: `curl -sf https://hub.docker.com/v2/repositories/contrast/mcp-contrast/tags/X.Y.Z`.
.claude/skills/release/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release orchestration

Runs the whole release documented in RELEASING.md, composing /update-changelog and /test-mcp-server. The flow is changelog-first: the audited changelog draft is the evidence for the version decision, and the release ticket and branch are created only after the human approves the version, so they are born with the right number. Publishing to Artifactory and DockerHub is irreversible, so the human gates below are mandatory, never skipped.

Usage

/release takes no arguments. The version always comes from the suggest-and-approve gate in Phase 3.

Re-entry

Releases fail mid-flight more than anywhere else. On re-entry, detect completed work from the repo and skip it: stamped changelog already on origin/main → go to Phase 5 or 6; release workflow already succeeded → go to Phase 7. The workflow itself is safe to re-dispatch because it reuses an existing vX.Y.Z tag at HEAD.

Phase 1 — Preflight (read-only)

  1. git fetch origin --tags -q. Confirm the working tree is clean and HEAD matches origin/main. If not, stop and tell the human.
  2. Verify the pr-tools plugin is available (check for /pr-tools:create-pr in the skill list). Phase 4 depends on it. If missing, stop and tell the human to install it per the CLAUDE.md "Required Plugins" section.
  3. Confirm CI is green: gh run list --branch main --workflow build.yml --limit 1 --json conclusion,headSha and check the run covers the current origin/main HEAD. Red or stale CI stops the release by default. The human may explicitly override for a known-flaky failure, record the override in the final report.
  4. Find the last release tag: git tag --sort=-v:refname | grep -E '^v[0-9]+\.[0-9]+\.[0-9]+$' | head -1.
  5. Enumerate the release content: git log --oneline --merges vLAST..origin/main, plus the same without --merges for direct commits. If the range is empty, there is nothing to release, stop.
  6. If every change in the range is internal (CI config, dependabot, refactors), ask the human whether to ship a dependency-bump release anyway. If yes, the Phase 2 draft must include a section summarizing the dependency updates (drawn from the dependabot PR titles, house style) so the stamped section is never empty.

Read the full file on GitHub · 179 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. 8d ago First seen · 179 lines · 106 tokens per session scan A 88d6e9faf2fe

Subscribe to this mod's changes

release is a skill published in the GitHub repository Contrast-Security-OSS/mcp-contrast (23 stars, last pushed 3d ago), licensed Apache-2.0. It adds 106 tokens to every session and 2,439 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.