Mythic-MCP: Skill for Claude Code

.claude/skills/ci-first-philosophy/SKILL.md

ci-first-philosophy is a skill for Claude Code from nbaertsch/Mythic-MCP. It costs 69 tokens per session (3,306 once invoked), scanned A, original, MIT.

A development approach that checks new code through integration and end-to-end tests in continuous integration (CI), the automated checks run by services such as GitHub Actions. End-to-end tests follow complete user journeys, while integration tests check real connections between parts such as databases and APIs.

In plain words
What is it for?
Use it when adding features or building applications to reason about system-wide effects, plan realistic test data, and validate complete workflows in CI.
Why use it?
It reduces the risk that code passes isolated tests but fails when the full application and its external services work together.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

This is nbaertsch/Mythic-MCP's own configuration. It tells Claude Code how to work on Mythic-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 Mythic-MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nbaertsch/Mythic-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/nbaertsch/Mythic-MCP/main/.claude/skills/ci-first-philosophy/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nbaertsch/Mythic-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 ci-first-philosophy

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/nbaertsch/mythic-mcp/ci-first-philosophy"><img src="https://agentmods.dev/badge/skills/nbaertsch/mythic-mcp/ci-first-philosophy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,306 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 $0.00069 $0.03306
Opus 5 $0.00034 $0.01653
Sonnet 5 $0.00014 $0.00661
Haiku 4.5 $0.00007 $0.00331

Measured 10d ago against content hash 3e2e0dc613a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ci-first-philosophy 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 10d 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/ci-first-philosophy/SKILL.md · 489 lines

How it starts

The opening of the file, as written. The whole thing — 489 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CI-First Development Philosophy

A proven methodology that shifts from isolated unit-test-driven TDD to comprehensive CI-validated, integration-first development.

Core Principles

1. Reason Before Coding

Always start by understanding the system, not just the function:

  • What is the desired outcome for the user/system?
  • What are the integration points (databases, APIs, services)?
  • What edge cases exist at integration boundaries?
  • What test data is needed for realistic testing?
  • How will this work in the full system context?

Pattern:

User Request → System Thinking → Integration Analysis → Test Planning → Implementation
     ↓              ↓                    ↓                    ↓              ↓
  "Add login"   Auth flow         DB, sessions         Test users    Code + Tests

2. Integration Over Isolation

Test Pyramid - Inverted for CI-First:

┌─────────────────────────────┐
│    End-to-End Tests         │  ← MOST IMPORTANT
│    (Full system flows)      │     Test real user journeys
├─────────────────────────────┤
│   Integration Tests         │  ← CORE VALIDATION
│   (Service interactions)    │     Real DB, APIs, services
├─────────────────────────────┤
│      Unit Tests             │  ← TARGETED ONLY
│   (Complex logic only)      │     Not exhaustive
└─────────────────────────────┘

Key Insight: Unit tests alone miss real-world issues. Integration and E2E tests catch:

  • Database constraint violations
  • API contract mismatches
  • Race conditions
  • Configuration errors
  • Service interaction bugs
  • Deployment issues

3. CI as Source of Truth

If it passes in CI, it works. If it fails in CI, it's broken.

  • CI tests run in production-like environment
  • CI validates full system integration
  • CI catches environment-specific issues
  • Local tests can lie (wrong versions, cached state, etc.)

Workflow:

1. Make change
2. Commit and push
3. Watch CI run
4. If fails → analyze, fix, repeat
5. If passes → trust it

Read the full file on GitHub · 489 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. 10d ago First seen · 489 lines · 69 tokens per session scan A 3e2e0dc613a0

Subscribe to this mod's changes

ci-first-philosophy is a skill published in the GitHub repository nbaertsch/Mythic-MCP (6 stars, last pushed 6mo ago), licensed MIT. It adds 69 tokens to every session and 3,306 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.