portainer-mcp: Skill for Claude Code

.claude/skills/portainer-mcp-release/SKILL.md

portainer-mcp-release is a skill for Claude Code from portainer/portainer-mcp. It costs 186 tokens per session (3,006 once invoked), scanned A, original, MIT.

A release procedure for portainer-mcp, a tool that connects software to Portainer, a platform for managing containers. It covers updating the embedded Portainer API specification when moving to a new Portainer minor version.

In plain words
What is it for?
Use it when upgrading the supported Portainer minor version, regenerating the patched API specification, refreshing profile documentation and inventories, and updating release version pins.
Why use it?
It reduces errors in a release that changes the API specification and requires related operation counts, tags, orphan records, documentation, and version references to stay aligned.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

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

Reuse

Borrowing it

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

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 portainer-mcp-release

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/portainer/portainer-mcp/portainer-mcp-release"><img src="https://agentmods.dev/badge/skills/portainer/portainer-mcp/portainer-mcp-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 186 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,006 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: 2 findings, up to medium

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 →

  • medium Agent Snooping · line 116
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 143
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00186 $0.03006
Opus 5 $0.00093 $0.01503
Sonnet 5 $0.00037 $0.00601
Haiku 4.5 $0.00019 $0.00301

Measured 12d ago against content hash da211bf1ce56, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

portainer-mcp-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 1 executable file (scripts/spec_deltas.py), 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.

.claude/skills/portainer-mcp-release/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

portainer-mcp release (spec bump)

This skill covers releases where the MCP minor moves with a new Portainer minor (e.g. 2.41.0 → 2.42.0). Per docs/versioning.md, the minor only moves when the embedded spec moves — patch-only releases (shaping fixes, dep bumps, profile tweaks against the same Portainer minor) follow a simpler flow that this skill does not cover. If unsure which kind you're cutting, the test is: did src/portainer_mcp/data/portainer-patched.yaml change? Spec bump → use this skill. Otherwise → patch release.

The release pipeline itself (PyPI publish via OIDC on tag push) is documented in docs/release.md; this skill is the spec-bump-specific work that has to land before the tag.

Why a skill for this

Spec bumps are infrequent (one per Portainer minor — quarterly-ish) and the work spans ten files. Most of those touches are mechanical version-pin updates, but two are easy to half-do:

  • Op/tag deltas in docs/profiles.md — the orphan table and default-coverage numbers are derived from the spec. Upstream often adds/removes/renames tags between minors. Stale numbers here mean users get the wrong picture of what the default profiles cover.
  • CHANGELOG entry — a one-liner that says "bumped spec" is much less useful than naming the deltas (operation count change, dropped tags). Skim of the changelog is how users decide whether the upgrade matters to them.

The script in scripts/spec_deltas.py automates the counting so neither slips.

The release in one breath

  1. Find the latest 2.X patch upstream.
  2. Branch off main as X.Y if you aren't already.
  3. make specs VERSION=X.Y.Z.
  4. uv run pytest and boot the server end-to-end.
  5. Run spec_deltas.py, capture the new numbers.
  6. Update nine files (see Step 6 checklist).
  7. Commit as Release X.Y.0, push branch.
  8. Open PR, merge to main (merge or rebase — not squash).
  9. From main, git tag X.Y.0 && git push origin X.Y.0.
  10. Watch the release workflow finish, verify on PyPI.

Read the full file on GitHub · 188 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. 12d ago First seen · 188 lines · 186 tokens per session scan A da211bf1ce56

Subscribe to this mod's changes

portainer-mcp-release is a skill published in the GitHub repository portainer/portainer-mcp (228 stars, last pushed 9d ago), licensed MIT. It adds 186 tokens to every session and 3,006 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.

Related

Other skills, from other repositories

hmem-release

Pre-publish checklist for hmem: skills synced, version bumped, tests green, nothing forgotten. Use before npm publish or when the user says 'release', 'publish', 'push a release', or 'neue Version'.

Bumblebiber/hmem · 50 tokens

release-and-publish

Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, pushes commits and tags, then publishes to each applicable destination. Assumes git wrapup (version bumps, changelog, commit, annotated tag) is already…

cyanheads/brapi-mcp-server · 112 tokens

release-and-publish

Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, pushes commits and tags, then publishes to each applicable destination. Assumes git wrapup (version bumps, changelog, commit, annotated tag) is already…

cyanheads/npi-providers-mcp-server · 112 tokens

deployment-patterns

Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.

affaan-m/ECC · 41 tokens

github

GitHub via gh CLI: PRs, issues, reviews, repos, auth.

NousResearch/hermes-agent · 19 tokens

goal-release

Cut a release end to end: use the draft-release skill to open the release PR and draft GitHub release, wait for CI to turn green, run the merge-pr skill to merge the release PR, then update the Homebrew formula from the published release assets. Use when the user wants to draft and merge a release in one go, or…

dyoshikawa/rulesync · 86 tokens