Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ValorVie/custom-skillsnpx agentmods add skills/valorvie/custom-skills/spec-driven-devWrote 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/valorvie/custom-skills/spec-driven-dev)<a href="https://agentmods.dev/skills/valorvie/custom-skills/spec-driven-dev"><img src="https://agentmods.dev/badge/skills/valorvie/custom-skills/spec-driven-dev.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 | $0.00067 | $0.01728 |
| Opus 5 | $0.00034 | $0.00864 |
| Sonnet 5 | $0.00013 | $0.00346 |
| Haiku 4.5 | $0.00007 | $0.00173 |
Grade A, and why
spec-driven-dev 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec-Driven Development Guide
Language: English | 繁體中文
Version: 1.1.1 Last Updated: 2026-01-30 Applicability: Claude Code Skills
Purpose
This skill guides you through Spec-Driven Development (SDD), ensuring changes are planned, documented, and approved before implementation.
Quick Reference
SDD Workflow
┌──────────────┐ ┌──────────────┐ ┌──────────────┐
│ Proposal │───▶│ Review │───▶│Implementation│
└──────────────┘ └──────────────┘ └──────────────┘
│
▼
┌──────────────┐ ┌──────────────┐
│ Archive │◀───│ Verification │
└──────────────┘ └──────────────┘
Workflow Stages
| Stage | Description | Output |
|---|---|---|
| Proposal | Define what to change and why | proposal.md |
| Review | Stakeholder approval | Approval record |
| Implementation | Execute approved spec | Code, tests, docs |
| Verification | Confirm implementation matches spec | Test results |
| Archive | Close and archive | Archived spec with links |
Core Principles
| Principle | Description |
|---|---|
| Evaluate First | Assess scope and sync needs before creating spec |
| Spec First | No functional changes without approved spec |
| Tool Priority | Use SDD tool commands when available |
| Methodology > Tooling | SDD works with any tool or manual process |
| Bidirectional Sync | Changes propagate to all related artifacts |
Pre-Spec Evaluation
Before creating a specification, answer these questions:
| Question | Options | Result |
|---|---|---|
| Scope? | Project-specific / Universal | Determines if Core Standard needed |
| Interactive? | Yes / No | Determines if Skill needed |
| User-triggered? | Yes / No | Determines if Command needed |
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.
- 4d ago First seen · 282 lines · 67 tokens per session scan A bb153ac70e29
spec-driven-dev is a skill published in the GitHub repository ValorVie/custom-skills (5 stars, last pushed 7d ago), licensed MIT. It adds 67 tokens to every session and 1,728 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
c-tasks
Manage tasks across Todoist (todoist-cli), Things 3 (things-cli), and Taskwarrior (task). Detects which tool is installed. Supports adding, listing, completing, and filtering tasks across all three managers.
c-jira
Manage Jira issues using jira (jira-cli). List and filter issues, create new tickets, transition issue status, manage sprints, and add comments — all from the terminal without opening a browser.
c-linear
Manage Linear issues and projects using the linear CLI. List and filter issues, create new issues, update status, start work on a branch, and create linked pull requests directly from the terminal.
github-issues
Manage GitHub issues, pull requests, CI runs, and repository operations via the gh CLI.
trello
Manage Trello boards, lists, and cards via the Trello REST API - create cards, move them, add comments and checklists.
profclaw-tickets
Create, update, and manage tickets in profClaw task manager.