mcp-flutter-apk-injector: Skill for Claude Code

.agents/skills/mcp-toolchain-orchestrator/SKILL.md

mcp-toolchain-orchestrator is a skill for Claude Code, Codex from MarwanDevSpace/mcp-flutter-apk-injector. It costs 28 tokens per session (579 once invoked), scanned A, original, MIT.

A release and maintenance process for MCP toolchains, which are systems that expose typed tools for AI assistants to call.

In plain words
What is it for?
Use it to maintain tool definitions, validate contracts, enforce verification gates, and keep a tool registry in sync.
Why use it?
It checks that public tools clearly describe their inputs, outputs, safety behaviour, and implementation before release.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md; mentions Gemini CLI.

This is MarwanDevSpace/mcp-flutter-apk-injector's own configuration. It tells Claude Code and Codex how to work on mcp-flutter-apk-injector 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-flutter-apk-injector configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MarwanDevSpace/mcp-flutter-apk-injector. 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/MarwanDevSpace/mcp-flutter-apk-injector/main/.agents/skills/mcp-toolchain-orchestrator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/MarwanDevSpace/mcp-flutter-apk-injector

Made for: Claude Code, Codex.

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 mcp-toolchain-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/marwandevspace/mcp-flutter-apk-injector/mcp-toolchain-orchestrator/github.svg)](https://agentmods.dev/skills/marwandevspace/mcp-flutter-apk-injector/mcp-toolchain-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/marwandevspace/mcp-flutter-apk-injector/mcp-toolchain-orchestrator"><img src="https://agentmods.dev/badge/skills/marwandevspace/mcp-flutter-apk-injector/mcp-toolchain-orchestrator/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 mcp-toolchain-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/marwandevspace/mcp-flutter-apk-injector/mcp-toolchain-orchestrator"><img src="https://agentmods.dev/badge/skills/marwandevspace/mcp-flutter-apk-injector/mcp-toolchain-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 579 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 $0.00028 $0.00579
Opus 5 $0.00014 $0.00290
Sonnet 5 $0.00006 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured 11d ago against content hash f96146fd0e4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-toolchain-orchestrator 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 11d 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.

.agents/skills/mcp-toolchain-orchestrator/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Toolchain Orchestrator Skill

This skill applies the canonical GEMINI.md release and tool-definition rules to mcp-flutter-apk-injector.

MCP contract rules

Every public primary tool must publish a human-readable title, short purpose-first description, complete input schema descriptions, output schema, and non-contradictory annotations. Keep long parameter documentation in the schema rather than duplicating it in the description.

Requirement Verification
Read-only behavior readOnlyHint: true, no target-workspace write, deterministic repeat behavior where claimed.
Mutating behavior destructiveHint: true, description says what paths/artifacts can change, and output lists changed files or output paths.
Input semantics All top-level and nested fields have descriptions; enums/defaults explain operational effects.
Output semantics Handler returns structuredContent matching the registered output schema as well as readable text JSON.
Handler parity Every public parameter is forwarded to implementation or removed; no inert advertised setting remains.

Prompt and command discipline

Prompt handlers must support zero-argument invocation. /merge and /revert are currently evidence/planning commands: neither should imply that split APKs were merged or workspace files restored without verification artifacts.

Release protocol

  1. Update package.json, package-lock.json, runtime version defaults, GEMINI.md, .agents/AGENTS.md, CHANGELOG.md, and release notes together.
  2. Run npm run lint, npm run typecheck, npm test, npm run build, and npm pack --dry-run.
  3. Inspect the emitted MCP contract in tests, including titles, annotations, input/output schemas, and prompt registration.
  4. Review git diff --check and the full staged diff before committing.
  5. Commit locally with a release-scoped message. Creating GitHub Releases, pushing to remote, publishing to npm, or changing public registry state requires explicit owner confirmation.
  6. After an approved public release, create the corresponding GitHub Release, use Glama’s Sync Server control, and verify the public listing’s version, latest release, schemas, annotations, and score capture.

Read the full file on GitHub · 38 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. 11d ago First seen · 38 lines · 28 tokens per session scan A f96146fd0e4e

Subscribe to this mod's changes

mcp-toolchain-orchestrator is a skill published in the GitHub repository MarwanDevSpace/mcp-flutter-apk-injector (5 stars, last pushed 8d ago), licensed MIT. It adds 28 tokens to every session and 579 once invoked, about $0.0001 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.