universal-mcp-sync: Skill for Claude Code

.gemini/skills/agentic-sdd-router/SKILL.md

agentic-sdd-router is a skill for Claude Code, Gemini CLI from nawodyaishan/universal-mcp-sync. It costs 49 tokens per session (780 once invoked), scanned A, original, MIT.

A routing skill for spec-driven development, a workflow where software is planned and checked through written requirements before and during coding. It chooses the appropriate phase, such as specification, planning, implementation, or verification.

In plain words
What is it for?
Use it when creating specifications, resolving requirements, making technical plans, breaking work into tasks, implementing approved work, reviewing changes, or checking for drift from the specification.
Why use it?
It helps keep work in the right order and reduces accidental jumps from a vague idea straight to code.

Skill for Claude CodeGemini CLI

Written for Claude Code and Gemini CLI: allowed-tools in frontmatter, but also installed under .gemini/. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

This is nawodyaishan/universal-mcp-sync's own configuration. It tells Claude Code and Gemini CLI how to work on universal-mcp-sync 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 universal-mcp-sync configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/nawodyaishan/Downloads/production-spec-driven-agentic-coding-guide.md.

Reuse

Borrowing it

Nothing to install: this file belongs to nawodyaishan/universal-mcp-sync. 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/nawodyaishan/universal-mcp-sync/main/.gemini/skills/agentic-sdd-router/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nawodyaishan/universal-mcp-sync

Made for: Claude Code, Gemini CLI.

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 agentic-sdd-router

README.md
[![agentmods](https://agentmods.dev/badge/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-router/github.svg)](https://agentmods.dev/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-router)
Your own site
<a href="https://agentmods.dev/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-router"><img src="https://agentmods.dev/badge/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-router/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 agentic-sdd-router

Your own site · 80×15
<a href="https://agentmods.dev/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-router"><img src="https://agentmods.dev/badge/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 780 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 $0.00049 $0.00780
Opus 5 $0.00024 $0.00390
Sonnet 5 $0.00010 $0.00156
Haiku 4.5 $0.00005 $0.00078

Measured 12d ago against content hash 814351d18479, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agentic-sdd-router 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.

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.

.gemini/skills/agentic-sdd-router/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic SDD Router

Use this skill first for spec-driven development work. It chooses the current phase, loads only the needed phase skill, and prevents accidental jumps from vague intent to code.

Source Backing

This workflow is based on:

  • Local guide: /Users/nawodyaishan/Downloads/production-spec-driven-agentic-coding-guide.md
  • GitHub Spec Kit workflow: constitution, specify, clarify, plan, tasks, analyze/checklist, implement
  • OpenAI Codex safety guidance: bounded sandboxing, explicit approvals for high-risk actions, and auditable tool activity

Phase Map

User intent Use skill
Set up SDD in a repo agentic-sdd-bootstrap
Write or improve product intent agentic-sdd-spec
Resolve unclear requirements agentic-sdd-spec
Create a technical plan agentic-sdd-plan
Review plan before coding agentic-sdd-architecture-review
Break plan into agent tasks agentic-sdd-tasks
Implement an approved task agentic-sdd-implement
Verify implementation or review diff agentic-sdd-verification-review
Detect drift, release notes, retrospective agentic-sdd-drift-retro

Required Order

For non-trivial production work, enforce this order:

bootstrap, if needed
-> spec
-> clarify, if needed
-> plan
-> architecture review and approval
-> tasks
-> implementation
-> verification and code review
-> drift check, release notes, retrospective

Routing Rules

  • If there is no spec.md for the requested work, route to agentic-sdd-spec.
  • If spec.md has open questions or ambiguous requirements, stay in agentic-sdd-spec.
  • If there is no plan.md, route to agentic-sdd-plan.
  • If plan.md exists but lacks approval, route to agentic-sdd-architecture-review.
  • If there is no tasks.md, route to agentic-sdd-tasks.
  • If implementation is requested and the plan is not approved, stop and ask for architecture approval.
  • If implementation is requested for high-risk areas, require explicit approval before edits:
    • dependencies or lockfiles
    • database migrations
    • auth or authorization
    • payments
    • secrets or credentials
    • production config, infrastructure, deployment
  • If the user asks for parallel agents or subagents, allow them only inside the implementation or review phases and only for bounded, disjoint work.

Read the full file on GitHub · 92 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. 12d ago First seen · 92 lines · 49 tokens per session scan A 814351d18479

Subscribe to this mod's changes

agentic-sdd-router is a skill published in the GitHub repository nawodyaishan/universal-mcp-sync (6 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 780 once invoked, about $0.0002 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.