Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Arenukvern/mcp_flutter --skill harness-engineering-lifecyclegit clone --depth 1 https://github.com/Arenukvern/mcp_flutterWrote 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.
[](https://agentmods.dev/skills/arenukvern/mcp_flutter/harness-engineering-lifecycle)<a href="https://agentmods.dev/skills/arenukvern/mcp_flutter/harness-engineering-lifecycle"><img src="https://agentmods.dev/badge/skills/arenukvern/mcp_flutter/harness-engineering-lifecycle.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.01385 |
| Opus 5 | $0.00044 | $0.00692 |
| Sonnet 5 | $0.00018 | $0.00277 |
| Haiku 4.5 | $0.00009 | $0.00138 |
Grade A, and why
harness-engineering-lifecycle 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 7d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- harness-engineering-lifecycle — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Engineering Lifecycle
Evolve a proven repo-local contract into a generalized, high-performance, declarative harness system, then safely dogfood those changes across a producer-consumer repository boundary. Start here only after the target repo has a steward.yaml contract and at least an H2 smoke proof; use mcp-harness-repo-maintainer before that.
When to use
- Evolving custom validation scripts into a central linter engine.
- Extending
stewardCLI features for large polyrepos. - Testing a local CLI/harness build against a sibling repository to catch path-resolution crashes or integration friction.
- Turning repeated local benchmark/probe findings into a reusable harness feature.
When not to use
- Initial
steward.yamladoption or first quick probe in one repo — usemcp-harness-repo-maintainer. - Skill creation, registry updates, or marketplace packaging — use
skill-authoring-lifecycleorplugin-marketplace-setup. - Product-specific diagnostics before a cold-start contract exists — first add a bounded action, probe, and scenario in the target repo.
Part 1: The Cascading Agent Surface (Architecture & Generalization)
When engineering a harness beyond one local contract, follow the Cascading Agent Surface guidelines. A strict separation of tools vs skills can fail once repo workflows span multiple packages, adapters, or consumers. Instead, link them using domain-agnostic abstractions:
- Layer 0 (The Embedded Agent Surface): The target application or engine must natively expose its internal state via explicit hooks (e.g., RPC or memory probes). Do not rely on brittle UI scraping or black-box testing.
- Layer 1 (The Protocol Adapter): Build generalized MCP servers or protocol adapters to connect to Layer 0. These tools provide raw visibility and actuation (e.g., taking screenshots, reading memory) but must contain NO business logic.
- Layer 2 (The Orchestrator): Build specialized harness CLIs that use their own automation/scripting to chain multiple Layer 1 actions together. The Orchestrator's primary job is the Fast Feedback Loop: it must emit structured, diagnostic JSON to pinpoint exactly what broke across boundaries.
- Layer 3 (The AI Wrapper): Following the
agentskills.iospec, Skills can and should contain thin-wrapper tools (scripts). The Skill acts as the AI's brain: it teaches the AI how to trigger Layer 2, interpret its complex JSON heuristics, and safely execute domain-specific recovery tools.
What ships with it
4 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.
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.
- 7d ago First seen · 85 lines · 88 tokens per session scan A 5329b6b5d1a4
harness-engineering-lifecycle is a skill published in the GitHub repository Arenukvern/mcp_flutter (373 stars, last pushed 11d ago), licensed MIT. It adds 88 tokens to every session and 1,385 once invoked, about $0.0004 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.
Other skills, from other repositories
patrol-e2e-testing
Use when writing E2E/integration tests, testing native interactions like permissions or system dialogs, capturing UI regressions, or validating cross-platform behavior (Patrol 4.x).
mockito
Use when generating mocks, stubbing methods, verifying interactions, capturing arguments, or choosing between mocks, fakes, and real objects (Mockito).
testing
Use when writing or reviewing Flutter/Dart tests (unit, widget, golden), fixing flaky tests, adding coverage, or choosing between unit and widget tests.
mocktail
Use when creating mocks, stubbing methods, verifying interactions, registering fallback values, or choosing between mocks, fakes, and real objects (Mocktail).
revenuecat-testing
Use when testing RevenueCat purchases/subscriptions, setting up sandbox testing, debugging a purchase/restore/trial, verifying entitlements or events, or writing an IAP QA plan.
testing-with-marionette
AI-driven Flutter E2E testing via VM Service CLI. Control running Flutter apps in debug mode for smoke tests, regression checks, exploratory testing, and UI automation. Trigger when user mentions E2E testing, UI automation, smoke tests, integration testing, test automation, controlling Flutter apps, VM Service…