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/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/vignesh2027/ai-agent-skills/spec-driven-development"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/spec-driven-development.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 | $0.00012 | $0.00650 |
| Opus 5.5 | $0.00005 | $0.00260 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 2mo ago), licensed MIT. It adds 12 tokens to every session and 650 once invoked, about $0.0000 per session on Opus 5.5. 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.
spec-driven-development compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| spec-driven-developmentvignesh2027/AI-AGENT-SKILLS | Skill | 2 | 2mo ago | MIT | A | 12 | Claude Code, Codex |
| cw-gatesHmbown/Codewhale | Skill | 41k | 1mo ago | MIT | A | 48 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 33 | Claude Code, Codex |
| eval-dataset-designbojieli/ai-agent-book | Skill | 57k | 1mo ago | Apache-2.0 | A | 138 | Claude Code, Codex |
| memory-systembojieli/ai-agent-book | Skill | 57k | 1mo ago | Apache-2.0 | A | 95 | Claude Code, Codex |
| release-helperSahir619/fable-method | Skill | 2.3k | 1mo ago | MIT | A | 43 | Claude Code |
| loongsuite-pilot-insightalibaba/loongsuite-pilot | Skill | 242 | yesterday | Apache-2.0 | A | 111 | Claude Code, Codex |