Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add vignesh2027/AI-AGENT-SKILLS --skill spec-driven-developmentgit clone --depth 1 https://github.com/vignesh2027/AI-AGENT-SKILLSWrote 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/vignesh2027/ai-agent-skills/spec-driven-development)<a href="https://agentmods.dev/skills/vignesh2027/ai-agent-skills/spec-driven-development"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/spec-driven-development.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 | $0.00012 | $0.00650 |
| Opus 5 | $0.00006 | $0.00325 |
| Sonnet 5 | $0.00002 | $0.00130 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade A, and why
spec-driven-development 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 7d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Specification-driven development forces clarity before commitment. A spec written before code reveals ambiguities, surfaces missing requirements, and creates a shared contract between implementer and reviewer. Code written without a spec is often solving the wrong problem correctly.
When to Use
- Before implementing any new feature or significant change
- When requirements are unclear or verbally communicated
- Before writing any public API or interface
- When multiple engineers will work on the same feature
Process
Step 1: Capture the raw requirement
Write down what you've been asked to build, in plain English, without interpretation. Include the source (ticket, conversation, PR comment).
Step 2: Identify stakeholders and success criteria
Answer: Who uses this? How do they know it works? What does failure look like?
Step 3: Write functional requirements
List what the system must do. Use "The system shall..." or "When X, then Y." Each requirement must be independently testable.
Step 4: Write non-functional requirements
Document: performance expectations, security constraints, accessibility requirements, scale targets, error handling expectations.
Step 5: Define the data model
Sketch the inputs, outputs, and state transitions. Identify what data must be stored, what must not be stored, and what can be computed.
Step 6: Define the interface contract
For APIs: endpoints, methods, request/response shapes, error codes. For UIs: wireframe or component tree, states (loading, empty, error, populated). For libraries: public function signatures and contracts.
Step 7: List open questions
Document every assumption you made and every question you don't have an answer to. Get answers before writing code.
Step 8: Get sign-off
Have the spec reviewed by at least one stakeholder before starting implementation. A spec that nobody reads is not a spec.
Anti-Rationalizations
"This feature is obvious — I don't need to write it down" If it's obvious, the spec takes 10 minutes. If it's not obvious, the spec saves days. Either way: write it.
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.
- 7d ago First seen · 74 lines · 12 tokens per session scan A 941d10539e07
spec-driven-development is a skill published in the GitHub repository vignesh2027/AI-AGENT-SKILLS (2 stars, last pushed 9d ago), licensed MIT. It adds 12 tokens to every session and 650 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
telegram
Owner-only Telegram text bridge and Mini App gateway for the existing Ouroboros interface.
claudexor
Use the local Claudexor control plane for harness-agnostic coding work across Claude Code, Codex, Cursor, and OpenCode. Use when a task benefits from route-aware harness and account selection, quota-aware account rotation, shared thread context, read-only planning or research, best-of-N execution, or cross-harness…
openai-docs
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use…
knowledge
The owner's knowledge base: a markdown folder that is also a typed graph of people, projects, decisions and terms, via the kb CLI. Use BEFORE answering anything about the owner, who they work with, what a project or term means, or what was decided and why; record durable facts unasked. Not for facts about the code.
Gmail, Google Calendar, Drive, Docs, Sheets and Contacts for a connected Google account: read and search mail, send and reply, book and move meetings, find files, read and write Docs and Sheets, look people up. Use whenever the user mentions their email, inbox, calendar, meetings, Drive, a Google Doc or Sheet.
wallet
Pay x402-payable endpoints in USDC from the sandbox wallet via the wallet CLI, under the owner's spending policy. Use when an API answers 402 Payment Required with an x402 challenge or a task needs a paid service: check the price, then ask; the owner approves each payment outside their auto-approve band.