What is agentic-sdd-implement?

A controlled implementation guide for one approved task from a Software Design Document (SDD), a written plan for a software change. It sets required reading, allowed files, safety checks, and verification rules.

Use it to implement a bounded task from specification files, follow project constraints, avoid forbidden files, and verify the result with the defined checks.

It keeps an implementation focused on the approved scope and requires extra approval for high-risk changes such as dependencies, databases, authentication, payments, secrets, or deployment settings.

How nawodyaishan/universal-mcp-sync configures Claude Code and Gemini

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-implement/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-implement/github.svg)](https://agentmods.dev/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-implement)

Your own site

<a href="https://agentmods.dev/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-implement"><img src="https://agentmods.dev/badge/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-implement/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-implement"><img src="https://agentmods.dev/badge/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-implement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 538 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.

Model	Per session	Once invoked
Fable 5.1	$0.00023	$0.00538
Opus 5	$0.00012	$0.00269
Sonnet 5	$0.00005	$0.00108
Haiku 4.5	$0.00002	$0.00054

Measured 8d ago against content hash 4f2e17c6e452, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agentic-sdd-implement 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 8d 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-implement/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic SDD Implement

Use this skill when implementing one approved task from specs/<feature>/tasks.md.

Goal

Implement exactly one bounded task or a small approved group of independent tasks. Keep the change scoped and verifiable.

Required Reading

.specify/memory/constitution.md
specs/<feature>/spec.md
specs/<feature>/plan.md
specs/<feature>/tasks.md
specs/<feature>/test-plan.md, if present
specs/<feature>/review.md, if present
relevant ADRs
relevant existing code and tests

Before Editing

Confirm:

the task is marked approved or safe to start
allowed and forbidden files are clear
verification command is defined
high-risk areas are not involved, or approval is explicit

High-Risk Approval Gate

Ask before touching:

package manager files or dependencies
database schema or migrations
auth, authorization, sessions, permissions
payments or billing
secrets, credentials, environment files
production config, infrastructure, deployment
destructive deletes or broad rewrites

Implementation Rules

Stay within allowed files unless you ask first.
Follow existing project patterns.
Prefer simple direct code over new abstractions.
Do not weaken tests to make code pass.
Update contracts, docs, and specs only when the task requires it.
Record any deviation from the plan.
Do not use subagents unless the user explicitly asked for delegated or parallel agent work.
If subagents are used, assign disjoint file ownership and run review before integration.

Verification

Run the task's verification command. Also run the narrowest relevant tests, typecheck, lint, or build available for the touched area.

If verification fails:

diagnose the failure
fix if within scope
report honestly if blocked or unrelated

Completion Report

Return:

task id
summary of changes
files changed
tests and commands run
results
deviations from the plan
follow-up risks or required review

Stop Conditions

Read the full file on GitHub · 91 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.

8d ago First seen · 91 lines · 23 tokens per session scan A 4f2e17c6e452

Subscribe to this mod's changes

agentic-sdd-implement is a skill published in the GitHub repository nawodyaishan/universal-mcp-sync (6 stars, last pushed 29d ago), licensed MIT. It adds 23 tokens to every session and 538 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.

Building agents Claude Code bubbletea claude claude-mcp cli codex

agent-manager

Run a fleet of AI coding agents as live tmux sessions with agent-manager. Use when a developer is running more than one coding agent, needs to see which one is working or blocked, wants to spawn another on an independent task, or wants to review an agent's diff without leaving the terminal.

YoanWai/agent-manager · 63 tokens

agent-manager-reference

Query agent-manager.dev's reference API and MCP server for documentation, the coding CLIs it manages, the tools its MCP server exposes, and the current release. Use instead of scraping the website's HTML.

YoanWai/agent-manager · 45 tokens

tui-design

Design, build, refactor, or review terminal interfaces—full-screen TUIs, interactive prompts, and command-line tools. Use for terminal-app layout and UX, CLI behavior, ncurses-style tools, dashboards, REPLs, fzf-like pickers, and libraries such as Bubble Tea, Ratatui, Textual, or Ink, including requests that name a…

gfargo/tui-design-skill · 135 tokens

universal-mcp-sync: Skill for Claude Code