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.
curl -O https://raw.githubusercontent.com/nawodyaishan/universal-mcp-sync/main/.gemini/skills/agentic-sdd-tasks/SKILL.mdgit clone --depth 1 https://github.com/nawodyaishan/universal-mcp-syncWrote 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/nawodyaishan/universal-mcp-sync/agentic-sdd-tasks)<a href="https://agentmods.dev/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-tasks"><img src="https://agentmods.dev/badge/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-tasks/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.
<a href="https://agentmods.dev/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-tasks"><img src="https://agentmods.dev/badge/skills/nawodyaishan/universal-mcp-sync/agentic-sdd-tasks.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00024 | $0.00447 |
| Opus 5 | $0.00012 | $0.00224 |
| Sonnet 5 | $0.00005 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
agentic-sdd-tasks 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.
What it actually says
Agentic SDD Tasks
Use this skill only after the architecture plan is approved or the user explicitly accepts the risk of proceeding.
Goal
Create specs/<feature>/tasks.md that an implementation agent can execute without reinterpreting the spec.
Required Reading
.specify/memory/constitution.mdspecs/<feature>/spec.mdspecs/<feature>/plan.mdspecs/<feature>/review.mdspecs/<feature>/test-plan.md, if present- relevant ADRs
Task Format
Each task must include:
- task id
- objective
- source artifacts
- allowed files or directories
- forbidden files or directories
- acceptance criteria
- verification command or observable result
- dependencies
- risk level
- approval needed, if any
- status
Task Design Rules
- Keep each task small enough for one focused implementation pass.
- Prefer vertical slices by user story when possible.
- Put tests before implementation when behavior is risky or TDD is requested.
- Mark parallel-safe tasks only when write sets are disjoint.
- Do not create tasks that require unapproved dependencies, migrations, auth/payment edits, secrets, production config, or deployment.
- Include documentation and contract updates as explicit tasks when behavior changes.
Recommended Sections
specs/<feature>/tasks.md should include:
- track summary
- prerequisites
- task list
- dependency order
- parallel-safe groups
- verification matrix
- blocked or approval-required work
Stop Conditions
Stop before writing implementation-ready tasks when:
- architecture review is not approved
- tasks would require guessing file ownership
- verification commands are unknown
- a task touches high-risk areas without approval
- dependencies between tasks are unclear
Output
Return task file path, number of tasks, blocked items, parallel-safe groups, and the first safe implementation task.
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.
- 10d ago First seen · 76 lines · 24 tokens per session scan A 7cd22cfac95b
agentic-sdd-tasks is a skill published in the GitHub repository nawodyaishan/universal-mcp-sync (6 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 447 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.
Other skills, from other repositories
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.
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.
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…
subagent-driven-development
Orchestrating sub-agents through TDD phases for complex features.
systematic-debugging
4-phase debugging protocol for diagnosing and fixing failing tests.
test-driven-development
Red-green-refactor TDD implementation cycle.